Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
February 2025
Return to Microsoft Research Lab – Redmond
Algorithms (Redmond)
Publications
Publications by Year
-
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
ICLR 2025 | February 2025
Inferentially-Private Private Information
Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
WWW 2025 | February 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
ICLR 2025 | February 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
ICLR 2025 | February 2025
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Guanghao Ye, Khiem Duc Pham, Xinzhi Zhang, Sivakanth Gopi, Baolin Peng, Beibin Li, Janardhan (Jana) Kulkarni, Huseyin Inan
February 2025
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
ICLR 2025 | February 2025
A Geometric Perspective on the Injective Norm of Sums of Random Tensors
Afonso S. Bandeira, Sivakanth Gopi, Haotian Jiang, Kevin Lucca, Thomas Rothvoss
STOC 2025 | January 2025
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sivakanth Gopi
January 2025
Sublinear Metric Steiner Tree via Improved Bounds for Set Cover
Sepideh Mahabadi, Mohammad Roghani, Jakub Tarnawski, Ali Vakilian
Innovations in Theoretical Computer Science (ITCS) | January 2025
-
How Generative AI Improves Supply Chain Management
Ishai Menache, Jeevan Pathuri, David Simchi-Levi, Tom Linton
Harvard Business Review | December 2024
Towards Foundation Models for Mixed Integer Linear Programming
Sirui Li, Janardhan (Jana) Kulkarni, Ishai Menache, Cathy Wu, Beibin Li
October 2024
Ranking with Multiple Objectives
Nikhil Devanur, Sivakanth Gopi
October 2024
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
NeurIPS 2024 | October 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
ECCV 2024 | July 2024
Statistic Maximal Leakage
Shuaiqi Wang, Zinan Lin, Giulia Fanti
IEEE International Symposium on Information Theory 2024 | July 2024
Streaming Algorithms for Connectivity Augmentation
Ce Jin, Michael Kapralov, Sepideh Mahabadi, Ali Vakilian
International Colloquium on Automata, Languages, and Programming (ICALP) | July 2024
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
June 2024
Optimal online discrepancy minimization
Janardhan (Jana) Kulkarni, Victor Reis, Thomas Rothvoss
STOC’24 | June 2024
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
NeurIPS 2024 | June 2024
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
CVPR 2024 | June 2024
Small Language Models for Application Interactions: A Case Study
Beibin Li, Yi Zhang, Sébastien Bubeck, Jeevan Pathuri, Ishai Menache
May 2024
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
ICLR 2024 | May 2024
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
AISTATS 2024 | May 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Improving the Training of Rectified Flows
Sangyun Lee, Zinan Lin, Giulia Fanti
NeurIPS 2024 | May 2024
Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
ICLR (TinyPapers) 2024 | May 2024
Rigidity matroids and linear algebraic matroids with applications to matrix completion and tensor codes
Joshua Brakensiek, Manik Dhar, Jiyang Gao, Sivakanth Gopi, Matt Larson
May 2024
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
TMLR | May 2024
Summary Statistic Privacy in Data Sharing
Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
IEEE Journal on Selected Areas in Information Theory | March 2024
Differentially Private Training of Mixture of Experts Models
Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim
PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024
Advancing differential privacy: where we are now and future directions for real-world deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang
Harvard Data Science Review | January 2024, Vol 6(1)
Convex Minimization with Integer Minima in O(n^4) Time
Haotian Jiang, Yin Tat Lee, Zhao Song, Lichen Zhang
SODA 2024 | January 2024
-
TinyGSM: achieving >80% on GSM8k with small language models
Bingbin Liu, Sébastien Bubeck, Ronen Eldan, Janardhan (Jana) Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang
3nd MATH-AI Workshop at NeurIPS’23 | December 2023
Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
Siddharth Gollapudi, Sepideh Mahabadi, Varun Sivashankar
NeurIPS 2023 | December 2023
Core-sets for Fair and Diverse Data Summarization
Sepideh Mahabadi, Stojan Trajanovski
NeurIPS 2023 | December 2023
Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan
NeurIPS 2023 | December 2023
Spotlight Presentation
Parallel Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
NeurIPS 2023 | December 2023
Spotlight Presentation
Spotlight Presentation
Tight Bounds for Volumetric Spanners and Applications
Aditya Bhaskara, Sepideh Mahabadi, Ali Vakilian
NeurIPS 2023 | December 2023
Training Private and Efficient Language Models with Synthetic Data from LLMs
Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
NeurIPS 2023 SoLaR Workshop | December 2023
Sparse Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
FOCS 2023 | November 2023
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu
Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023
AG codes achieve list decoding capacity over contant-sized fields
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi, Zihan Zhang
STOC 2024 | October 2023
Generalized GM-MDS: Polynomial Codes are Higher Order MDS
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
STOC 2024 | October 2023
Improved Diversity Maximization Algorithms for Matching and Pseudoforest
Sepideh Mahabadi, Shyam Narayanan
APPROX | September 2023
Approximation Algorithms for Fair Range Clustering
Sèdjro S. Hotegni, Sepideh Mahabadi, Ali Vakilian
ICML | July 2023
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
ICML 2023 | July 2023
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
NeurIPS 2023 | June 2023
Outstanding Paper Award
Resolving Matrix Spencer Conjecture Up to Poly-logarithmic Rank
Nikhil Bansal, Haotian Jiang, Raghu Meka
STOC 2023 | June 2023
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
International Conference on Learning Representations (ICLR) 2023 | May 2023
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
COLT 2023 | February 2023
-
A construction of Maximally Recoverable LRCs for small number of local groups
Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Improved Field Size Bounds for Higher Order MDS Codes
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni
NeurIPS 2022 | November 2022
When does differentially private learning not suffer in high dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
NeurIPS’22 | November 2022
Composable Coresets for Constrained Determinant Maximization and Beyond
Sepideh Mahabadi, Thuy-Duong Vuong
November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Adaptive Sketches for Robust Regression with Importance Sampling
Sepideh Mahabadi, David P. Woodruff, Samson Zhou
RANDOM | September 2022
Sampling Near Neighbors in Search for Fairness
Martin Aumüller, Sariel Har-Peled, Sepideh Mahabadi, Rasmus Pagh, Francesco Silvestri
Communications of the ACM (CACM) | August 2022
Private Convex Optimization in General Norms
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
SODA 2023 | July 2022
Generic Reed-Solomon codes achieve list-decoding capacity
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
STOC 2023 | June 2022
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Differentially private fine-tuning of language models
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
ICLR 2022 | April 2022
Private Convex Optimization via Exponential Mechanism
Sivakanth Gopi, Yin Tat Lee, Daogao Liu
COLT 2022 | March 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
-
Differentially private n-gram extraction
Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin
NeurIPS 2021 | December 2021
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Scaling DNA data storage with nanoscale electrode wells
Bichlien Nguyen, Christopher Takahashi, Gagan Gupta, Jake Smith, Richard Rouse, Paul Berndt, Sergey Yekhanin, David Ward, Siena Ang, Patrick Garvan, Hsing-Yeh Parker, Rob Carlson, Douglas Carmean, Luis Ceze, Karin Strauss
Science Advances | November 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Batch optimization for DNA synthesis
Konstantin Makarychev, Miklos Racz, Cyrus Rashtchian, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Lower Bounds for Maximally Recoverable Tensor Code and Higher Order MDS Codes
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
IEEE Transactions on Information Theory | July 2021
Scheduling Opportunistic Links in Two-Tiered Reconfigurable Datacenters
Janardhan (Jana) Kulkarni, Stefan Schmid, Paweł Schmidt
ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) 2021 | July 2021
Trellis BMA: coded trace reconstruction on IDS channels for DNA storage
Sundara Rajan Srinivasavaradhan, Sivakanth Gopi, Henry Pfister, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Numerical Composition of Differential Privacy
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
NeurIPS 2021 | June 2021
Spotlight at NeurIPS 2021.
Consistent k-Median: Simpler, Better and Robust
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021 | April 2021
Differentially Private Correlation Clustering
Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni
2021 International Conference on Machine Learning | February 2021
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat
NeurIPS 2021 | February 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
-
Improved Maximally Recoverable LRCs using Skew Polynomials
Sivakanth Gopi, Venkatesan Guruswami
IEEE Transactions on Information Theory | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
On the Facility Location Problem in Online and Dynamic Models
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
APPROX-RANDOM | August 2020
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang
Conference on Learning Theory (COLT) 2020 | July 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020
Publications by Research Area
-
Sublinear Metric Steiner Tree via Improved Bounds for Set Cover
Sepideh Mahabadi, Mohammad Roghani, Jakub Tarnawski, Ali Vakilian
Innovations in Theoretical Computer Science (ITCS) | January 2025
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sivakanth Gopi
January 2025
Ranking with Multiple Objectives
Nikhil Devanur, Sivakanth Gopi
October 2024
Streaming Algorithms for Connectivity Augmentation
Ce Jin, Michael Kapralov, Sepideh Mahabadi, Ali Vakilian
International Colloquium on Automata, Languages, and Programming (ICALP) | July 2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
Optimal online discrepancy minimization
Janardhan (Jana) Kulkarni, Victor Reis, Thomas Rothvoss
STOC’24 | June 2024
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
TMLR | May 2024
Differentially Private Training of Mixture of Experts Models
Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim
PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024
Convex Minimization with Integer Minima in O(n^4) Time
Haotian Jiang, Yin Tat Lee, Zhao Song, Lichen Zhang
SODA 2024 | January 2024
Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan
NeurIPS 2023 | December 2023
Spotlight Presentation
Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
Siddharth Gollapudi, Sepideh Mahabadi, Varun Sivashankar
NeurIPS 2023 | December 2023
Tight Bounds for Volumetric Spanners and Applications
Aditya Bhaskara, Sepideh Mahabadi, Ali Vakilian
NeurIPS 2023 | December 2023
Parallel Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
NeurIPS 2023 | December 2023
Spotlight Presentation
Spotlight Presentation
Core-sets for Fair and Diverse Data Summarization
Sepideh Mahabadi, Stojan Trajanovski
NeurIPS 2023 | December 2023
Sparse Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
FOCS 2023 | November 2023
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu
Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023
AG codes achieve list decoding capacity over contant-sized fields
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi, Zihan Zhang
STOC 2024 | October 2023
Generalized GM-MDS: Polynomial Codes are Higher Order MDS
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
STOC 2024 | October 2023
Improved Diversity Maximization Algorithms for Matching and Pseudoforest
Sepideh Mahabadi, Shyam Narayanan
APPROX | September 2023
Approximation Algorithms for Fair Range Clustering
Sèdjro S. Hotegni, Sepideh Mahabadi, Ali Vakilian
ICML | July 2023
Resolving Matrix Spencer Conjecture Up to Poly-logarithmic Rank
Nikhil Bansal, Haotian Jiang, Raghu Meka
STOC 2023 | June 2023
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
COLT 2023 | February 2023
A construction of Maximally Recoverable LRCs for small number of local groups
Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Improved Field Size Bounds for Higher Order MDS Codes
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni
NeurIPS 2022 | November 2022
When does differentially private learning not suffer in high dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
NeurIPS’22 | November 2022
Composable Coresets for Constrained Determinant Maximization and Beyond
Sepideh Mahabadi, Thuy-Duong Vuong
November 2022
Adaptive Sketches for Robust Regression with Importance Sampling
Sepideh Mahabadi, David P. Woodruff, Samson Zhou
RANDOM | September 2022
Sampling Near Neighbors in Search for Fairness
Martin Aumüller, Sariel Har-Peled, Sepideh Mahabadi, Rasmus Pagh, Francesco Silvestri
Communications of the ACM (CACM) | August 2022
Private Convex Optimization in General Norms
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
SODA 2023 | July 2022
Generic Reed-Solomon codes achieve list-decoding capacity
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
STOC 2023 | June 2022
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Differentially private fine-tuning of language models
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
ICLR 2022 | April 2022
Private Convex Optimization via Exponential Mechanism
Sivakanth Gopi, Yin Tat Lee, Daogao Liu
COLT 2022 | March 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
Differentially private n-gram extraction
Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Lower Bounds for Maximally Recoverable Tensor Code and Higher Order MDS Codes
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
IEEE Transactions on Information Theory | July 2021
Scheduling Opportunistic Links in Two-Tiered Reconfigurable Datacenters
Janardhan (Jana) Kulkarni, Stefan Schmid, Paweł Schmidt
ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) 2021 | July 2021
Trellis BMA: coded trace reconstruction on IDS channels for DNA storage
Sundara Rajan Srinivasavaradhan, Sivakanth Gopi, Henry Pfister, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Batch optimization for DNA synthesis
Konstantin Makarychev, Miklos Racz, Cyrus Rashtchian, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Numerical Composition of Differential Privacy
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
NeurIPS 2021 | June 2021
Spotlight at NeurIPS 2021.
Consistent k-Median: Simpler, Better and Robust
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021 | April 2021
Differentially Private Correlation Clustering
Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni
2021 International Conference on Machine Learning | February 2021
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat
NeurIPS 2021 | February 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
Improved Maximally Recoverable LRCs using Skew Polynomials
Sivakanth Gopi, Venkatesan Guruswami
IEEE Transactions on Information Theory | December 2020
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
On the Facility Location Problem in Online and Dynamic Models
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
APPROX-RANDOM | August 2020
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang
Conference on Learning Theory (COLT) 2020 | July 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020
-
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
February 2025
Inferentially-Private Private Information
Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
WWW 2025 | February 2025
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
ICLR 2025 | February 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
ICLR 2025 | February 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
ICLR 2025 | February 2025
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
ICLR 2025 | February 2025
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Guanghao Ye, Khiem Duc Pham, Xinzhi Zhang, Sivakanth Gopi, Baolin Peng, Beibin Li, Janardhan (Jana) Kulkarni, Huseyin Inan
February 2025
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sivakanth Gopi
January 2025
How Generative AI Improves Supply Chain Management
Ishai Menache, Jeevan Pathuri, David Simchi-Levi, Tom Linton
Harvard Business Review | December 2024
Towards Foundation Models for Mixed Integer Linear Programming
Sirui Li, Janardhan (Jana) Kulkarni, Ishai Menache, Cathy Wu, Beibin Li
October 2024
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
NeurIPS 2024 | October 2024
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
ECCV 2024 | July 2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
Statistic Maximal Leakage
Shuaiqi Wang, Zinan Lin, Giulia Fanti
IEEE International Symposium on Information Theory 2024 | July 2024
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
June 2024
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
NeurIPS 2024 | June 2024
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
CVPR 2024 | June 2024
Small Language Models for Application Interactions: A Case Study
Beibin Li, Yi Zhang, Sébastien Bubeck, Jeevan Pathuri, Ishai Menache
May 2024
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
ICLR 2024 | May 2024
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
AISTATS 2024 | May 2024
Improving the Training of Rectified Flows
Sangyun Lee, Zinan Lin, Giulia Fanti
NeurIPS 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
ICLR (TinyPapers) 2024 | May 2024
Summary Statistic Privacy in Data Sharing
Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
IEEE Journal on Selected Areas in Information Theory | March 2024
TinyGSM: achieving >80% on GSM8k with small language models
Bingbin Liu, Sébastien Bubeck, Ronen Eldan, Janardhan (Jana) Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang
3nd MATH-AI Workshop at NeurIPS’23 | December 2023
Training Private and Efficient Language Models with Synthetic Data from LLMs
Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
NeurIPS 2023 SoLaR Workshop | December 2023
Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan
NeurIPS 2023 | December 2023
Spotlight Presentation
Core-sets for Fair and Diverse Data Summarization
Sepideh Mahabadi, Stojan Trajanovski
NeurIPS 2023 | December 2023
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
ICML 2023 | July 2023
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
NeurIPS 2023 | June 2023
Outstanding Paper Award
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
International Conference on Learning Representations (ICLR) 2023 | May 2023
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni
NeurIPS 2022 | November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
-
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
February 2025
Inferentially-Private Private Information
Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
WWW 2025 | February 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
ICLR 2025 | February 2025
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
NeurIPS 2024 | October 2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
Statistic Maximal Leakage
Shuaiqi Wang, Zinan Lin, Giulia Fanti
IEEE International Symposium on Information Theory 2024 | July 2024
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
TMLR | May 2024
Summary Statistic Privacy in Data Sharing
Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
IEEE Journal on Selected Areas in Information Theory | March 2024
Advancing differential privacy: where we are now and future directions for real-world deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang
Harvard Data Science Review | January 2024, Vol 6(1)
Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan
NeurIPS 2023 | December 2023
Spotlight Presentation
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
NeurIPS 2023 | June 2023
Outstanding Paper Award
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
International Conference on Learning Representations (ICLR) 2023 | May 2023
Private Convex Optimization in General Norms
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
SODA 2023 | July 2022
Private Convex Optimization via Exponential Mechanism
Sivakanth Gopi, Yin Tat Lee, Daogao Liu
COLT 2022 | March 2022
Numerical Composition of Differential Privacy
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
NeurIPS 2021 | June 2021
Spotlight at NeurIPS 2021.
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat
NeurIPS 2021 | February 2021
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang
Conference on Learning Theory (COLT) 2020 | July 2020
-
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
ICLR 2025 | February 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
ICLR 2025 | February 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
ICLR 2025 | February 2025
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
ICLR 2025 | February 2025
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
ECCV 2024 | July 2024
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
CVPR 2024 | June 2024
Improving the Training of Rectified Flows
Sangyun Lee, Zinan Lin, Giulia Fanti
NeurIPS 2024 | May 2024
Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
ICLR (TinyPapers) 2024 | May 2024
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
ICML 2023 | July 2023
-
A Geometric Perspective on the Injective Norm of Sums of Random Tensors
Afonso S. Bandeira, Sivakanth Gopi, Haotian Jiang, Kevin Lucca, Thomas Rothvoss
STOC 2025 | January 2025
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sivakanth Gopi
January 2025
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Rigidity matroids and linear algebraic matroids with applications to matrix completion and tensor codes
Joshua Brakensiek, Manik Dhar, Jiyang Gao, Sivakanth Gopi, Matt Larson
May 2024
Advancing differential privacy: where we are now and future directions for real-world deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang
Harvard Data Science Review | January 2024, Vol 6(1)
Convex Minimization with Integer Minima in O(n^4) Time
Haotian Jiang, Yin Tat Lee, Zhao Song, Lichen Zhang
SODA 2024 | January 2024
Parallel Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
NeurIPS 2023 | December 2023
Spotlight Presentation
Spotlight Presentation
Sparse Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
FOCS 2023 | November 2023
AG codes achieve list decoding capacity over contant-sized fields
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi, Zihan Zhang
STOC 2024 | October 2023
Generalized GM-MDS: Polynomial Codes are Higher Order MDS
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
STOC 2024 | October 2023
Resolving Matrix Spencer Conjecture Up to Poly-logarithmic Rank
Nikhil Bansal, Haotian Jiang, Raghu Meka
STOC 2023 | June 2023
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
COLT 2023 | February 2023
A construction of Maximally Recoverable LRCs for small number of local groups
Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Improved Field Size Bounds for Higher Order MDS Codes
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Private Convex Optimization in General Norms
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
SODA 2023 | July 2022
Generic Reed-Solomon codes achieve list-decoding capacity
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
STOC 2023 | June 2022
Private Convex Optimization via Exponential Mechanism
Sivakanth Gopi, Yin Tat Lee, Daogao Liu
COLT 2022 | March 2022
Lower Bounds for Maximally Recoverable Tensor Code and Higher Order MDS Codes
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
IEEE Transactions on Information Theory | July 2021
Trellis BMA: coded trace reconstruction on IDS channels for DNA storage
Sundara Rajan Srinivasavaradhan, Sivakanth Gopi, Henry Pfister, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Batch optimization for DNA synthesis
Konstantin Makarychev, Miklos Racz, Cyrus Rashtchian, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Numerical Composition of Differential Privacy
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
NeurIPS 2021 | June 2021
Spotlight at NeurIPS 2021.
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat
NeurIPS 2021 | February 2021
Improved Maximally Recoverable LRCs using Skew Polynomials
Sivakanth Gopi, Venkatesan Guruswami
IEEE Transactions on Information Theory | December 2020
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang
Conference on Learning Theory (COLT) 2020 | July 2020
-
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Streaming Algorithms for Connectivity Augmentation
Ce Jin, Michael Kapralov, Sepideh Mahabadi, Ali Vakilian
International Colloquium on Automata, Languages, and Programming (ICALP) | July 2024
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Scaling DNA data storage with nanoscale electrode wells
Bichlien Nguyen, Christopher Takahashi, Gagan Gupta, Jake Smith, Richard Rouse, Paul Berndt, Sergey Yekhanin, David Ward, Siena Ang, Patrick Garvan, Hsing-Yeh Parker, Rob Carlson, Douglas Carmean, Luis Ceze, Karin Strauss
Science Advances | November 2021
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
-
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
ICLR 2024 | May 2024
-
Scaling DNA data storage with nanoscale electrode wells
Bichlien Nguyen, Christopher Takahashi, Gagan Gupta, Jake Smith, Richard Rouse, Paul Berndt, Sergey Yekhanin, David Ward, Siena Ang, Patrick Garvan, Hsing-Yeh Parker, Rob Carlson, Douglas Carmean, Luis Ceze, Karin Strauss
Science Advances | November 2021
-
Scaling DNA data storage with nanoscale electrode wells
Bichlien Nguyen, Christopher Takahashi, Gagan Gupta, Jake Smith, Richard Rouse, Paul Berndt, Sergey Yekhanin, David Ward, Siena Ang, Patrick Garvan, Hsing-Yeh Parker, Rob Carlson, Douglas Carmean, Luis Ceze, Karin Strauss
Science Advances | November 2021
-
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
Publications by Type
-
Inferentially-Private Private Information
Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
WWW 2025 | February 2025
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
ICLR 2025 | February 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
ICLR 2025 | February 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
ICLR 2025 | February 2025
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
ICLR 2025 | February 2025
Sublinear Metric Steiner Tree via Improved Bounds for Set Cover
Sepideh Mahabadi, Mohammad Roghani, Jakub Tarnawski, Ali Vakilian
Innovations in Theoretical Computer Science (ITCS) | January 2025
A Geometric Perspective on the Injective Norm of Sums of Random Tensors
Afonso S. Bandeira, Sivakanth Gopi, Haotian Jiang, Kevin Lucca, Thomas Rothvoss
STOC 2025 | January 2025
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
NeurIPS 2024 | October 2024
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Streaming Algorithms for Connectivity Augmentation
Ce Jin, Michael Kapralov, Sepideh Mahabadi, Ali Vakilian
International Colloquium on Automata, Languages, and Programming (ICALP) | July 2024
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
ECCV 2024 | July 2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
ICML 2024 | July 2024
Spotlight
Statistic Maximal Leakage
Shuaiqi Wang, Zinan Lin, Giulia Fanti
IEEE International Symposium on Information Theory 2024 | July 2024
Optimal online discrepancy minimization
Janardhan (Jana) Kulkarni, Victor Reis, Thomas Rothvoss
STOC’24 | June 2024
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
NeurIPS 2024 | June 2024
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
CVPR 2024 | June 2024
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
ICLR 2024 | May 2024
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
ICLR 2024 | May 2024
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
ICLR 2024 | May 2024
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
AISTATS 2024 | May 2024
Improving the Training of Rectified Flows
Sangyun Lee, Zinan Lin, Giulia Fanti
NeurIPS 2024 | May 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
ICLR (TinyPapers) 2024 | May 2024
Differentially Private Training of Mixture of Experts Models
Pierre Tholoniat, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Robert Sim
PPAI-24: The 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence | February 2024
Convex Minimization with Integer Minima in O(n^4) Time
Haotian Jiang, Yin Tat Lee, Zhao Song, Lichen Zhang
SODA 2024 | January 2024
TinyGSM: achieving >80% on GSM8k with small language models
Bingbin Liu, Sébastien Bubeck, Ronen Eldan, Janardhan (Jana) Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang
3nd MATH-AI Workshop at NeurIPS’23 | December 2023
Training Private and Efficient Language Models with Synthetic Data from LLMs
Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
NeurIPS 2023 SoLaR Workshop | December 2023
Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni, Piotr Indyk, Sepideh Mahabadi, Shyam Narayanan
NeurIPS 2023 | December 2023
Spotlight Presentation
Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
Siddharth Gollapudi, Sepideh Mahabadi, Varun Sivashankar
NeurIPS 2023 | December 2023
Tight Bounds for Volumetric Spanners and Applications
Aditya Bhaskara, Sepideh Mahabadi, Ali Vakilian
NeurIPS 2023 | December 2023
Parallel Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
NeurIPS 2023 | December 2023
Spotlight Presentation
Spotlight Presentation
Core-sets for Fair and Diverse Data Summarization
Sepideh Mahabadi, Stojan Trajanovski
NeurIPS 2023 | December 2023
Sparse Submodular Function Minimization
Andrei Graur, Haotian Jiang, Aaron Sidford
FOCS 2023 | November 2023
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
Ruixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A. Inan, Janardhan (Jana) Kulkarni, Xia Hu
Empirical Methods in Natural Language Processing (EMNLP 2023) | October 2023
AG codes achieve list decoding capacity over contant-sized fields
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi, Zihan Zhang
STOC 2024 | October 2023
Generalized GM-MDS: Polynomial Codes are Higher Order MDS
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
STOC 2024 | October 2023
Improved Diversity Maximization Algorithms for Matching and Pseudoforest
Sepideh Mahabadi, Shyam Narayanan
APPROX | September 2023
Approximation Algorithms for Fair Range Clustering
Sèdjro S. Hotegni, Sepideh Mahabadi, Ali Vakilian
ICML | July 2023
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
ICML 2023 | July 2023
Resolving Matrix Spencer Conjecture Up to Poly-logarithmic Rank
Nikhil Bansal, Haotian Jiang, Raghu Meka
STOC 2023 | June 2023
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
NeurIPS 2023 | June 2023
Outstanding Paper Award
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan (Jana) Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
International Conference on Learning Representations (ICLR) 2023 | May 2023
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
COLT 2023 | February 2023
A construction of Maximally Recoverable LRCs for small number of local groups
Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Improved Field Size Bounds for Higher Order MDS Codes
Joshua Brakensiek, Manik Dhar, Sivakanth Gopi
ISIT 2023 | December 2022
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni
NeurIPS 2022 | November 2022
When does differentially private learning not suffer in high dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
NeurIPS’22 | November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Adaptive Sketches for Robust Regression with Importance Sampling
Sepideh Mahabadi, David P. Woodruff, Samson Zhou
RANDOM | September 2022
Private Convex Optimization in General Norms
Sivakanth Gopi, Yin Tat Lee, Daogao Liu, Rouqi Shen, Kevin Tian
SODA 2023 | July 2022
Generic Reed-Solomon codes achieve list-decoding capacity
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
STOC 2023 | June 2022
Differentially private fine-tuning of language models
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Gautam Kamath, Janardhan (Jana) Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
ICLR 2022 | April 2022
Private Convex Optimization via Exponential Mechanism
Sivakanth Gopi, Yin Tat Lee, Daogao Liu
COLT 2022 | March 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
Differentially private n-gram extraction
Kunho Kim, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Sergey Yekhanin
NeurIPS 2021 | December 2021
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Scheduling Opportunistic Links in Two-Tiered Reconfigurable Datacenters
Janardhan (Jana) Kulkarni, Stefan Schmid, Paweł Schmidt
ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) 2021 | July 2021
Trellis BMA: coded trace reconstruction on IDS channels for DNA storage
Sundara Rajan Srinivasavaradhan, Sivakanth Gopi, Henry Pfister, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Batch optimization for DNA synthesis
Konstantin Makarychev, Miklos Racz, Cyrus Rashtchian, Sergey Yekhanin
International Symposium on Information Theory (ISIT) | July 2021
Numerical Composition of Differential Privacy
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
NeurIPS 2021 | June 2021
Spotlight at NeurIPS 2021.
Consistent k-Median: Simpler, Better and Robust
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021 | April 2021
Differentially Private Correlation Clustering
Mark Bun, Marek Eliás, Janardhan (Jana) Kulkarni
2021 International Conference on Machine Learning | February 2021
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Yin Tat Lee, Judy Hanwen Shen, Uthaipon Tantipongpipat
NeurIPS 2021 | February 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
On the Facility Location Problem in Online and Dynamic Models
Xiangyu Guo, Janardhan (Jana) Kulkarni, Shi Li, Jiayi Xian
APPROX-RANDOM | August 2020
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan (Jana) Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang
Conference on Learning Theory (COLT) 2020 | July 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020
-
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
February 2025
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Guanghao Ye, Khiem Duc Pham, Xinzhi Zhang, Sivakanth Gopi, Baolin Peng, Beibin Li, Janardhan (Jana) Kulkarni, Huseyin Inan
February 2025
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sivakanth Gopi
January 2025
Ranking with Multiple Objectives
Nikhil Devanur, Sivakanth Gopi
October 2024
Rigidity matroids and linear algebraic matroids with applications to matrix completion and tensor codes
Joshua Brakensiek, Manik Dhar, Jiyang Gao, Sivakanth Gopi, Matt Larson
May 2024
Composable Coresets for Constrained Determinant Maximization and Beyond
Sepideh Mahabadi, Thuy-Duong Vuong
November 2022
Unveiling Transformers with LEGO: a synthetic reasoning task
Yi Zhang, Arturs Backurs, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Tal Wagner
June 2022
-
How Generative AI Improves Supply Chain Management
Ishai Menache, Jeevan Pathuri, David Simchi-Levi, Tom Linton
Harvard Business Review | December 2024
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
TMLR | May 2024
Summary Statistic Privacy in Data Sharing
Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
IEEE Journal on Selected Areas in Information Theory | March 2024
Advancing differential privacy: where we are now and future directions for real-world deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Da Yu, Sergey Yekhanin, Huanyu Zhang, Wanrong Zhang
Harvard Data Science Review | January 2024, Vol 6(1)
Sampling Near Neighbors in Search for Fairness
Martin Aumüller, Sariel Har-Peled, Sepideh Mahabadi, Rasmus Pagh, Francesco Silvestri
Communications of the ACM (CACM) | August 2022
Scaling DNA data storage with nanoscale electrode wells
Bichlien Nguyen, Christopher Takahashi, Gagan Gupta, Jake Smith, Richard Rouse, Paul Berndt, Sergey Yekhanin, David Ward, Siena Ang, Patrick Garvan, Hsing-Yeh Parker, Rob Carlson, Douglas Carmean, Luis Ceze, Karin Strauss
Science Advances | November 2021
Lower Bounds for Maximally Recoverable Tensor Code and Higher Order MDS Codes
Joshua Brakensiek, Sivakanth Gopi, Visu Makam
IEEE Transactions on Information Theory | July 2021
Improved Maximally Recoverable LRCs using Skew Polynomials
Sivakanth Gopi, Venkatesan Guruswami
IEEE Transactions on Information Theory | December 2020
-
Towards Foundation Models for Mixed Integer Linear Programming
Sirui Li, Janardhan (Jana) Kulkarni, Ishai Menache, Cathy Wu, Beibin Li
October 2024
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
June 2024
Small Language Models for Application Interactions: A Case Study
Beibin Li, Yi Zhang, Sébastien Bubeck, Jeevan Pathuri, Ishai Menache
May 2024