Microsoft presentation schedule
Sunday, June 9
2:00 PM | Room 104 (Workshop)
Real World Reinforcement Learning Workshop
Organizers: John Langford, Rodrigo Kumpera, Cheng Tan, Jack Gerrits, Paul Mineiro, Alexey Taymanov
Monday, June 10
1:00 PM–3:15 PM | Grand Ballroom (Tutorial)
Neural Approaches to Conversational AI
Michel Galley, Jianfeng Gao
Tuesday, June 11
11:25 AM–11:30 AM | Grand Ballroom (Oral)
On Certifying Non-Uniform Bounds against Adversarial Attacks
Chen Liu, Ryota Tomioka, Volkan Cevher
11:40 AM–12:00 PM | Grand Ballroom (Oral)
Adversarial Examples from Computational Constraints
Sebastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn
11:40 AM–12:00 PM | Seaside Ballroom (Oral)
Contextual Memory Trees
Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro
12:00 PM–12:05 PM | Room 104 (Oral)
A Composite Randomized Incremental Gradient Method
Junyu Zhang, Lin Xiao
12:00 PM–12:05 PM | Room 101 (Oral)
Stein Point Markov Chain Monte Carlo
Wilson Ye Chen, Alessandro Barp, Francois-Xavier Briol, Jackson Gorham, Mark Girolami, Lester Mackey, Chris Oates
2:00 PM–2:20 PM | Room 102 (Oral)
Generalized Approximate Survey Propagation for High-Dimensional Estimation
Carlo Lucibello, Luca Saglietti, Yue Lu
2:00 PM–2:20 PM | Grand Ballroom (Oral)
On Learning Invariant Representations for Domain Adaptation
Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoff Gordon
2:00 PM–2:20 PM | Room 104 (Oral)
Safe Policy Improvement with Baseline Bootstrapping
Romain Laroche, Paul Trichelair, Remi Tachet des Combes
4:40 PM–5:00 PM | Room 102 (Oral)
Locally Private Bayesian Inference for Count Models
Aaron Schein, Zhiwei Steven Wu, Alexandra Schofield, Mingyuan Zhou, Hanna Wallach
5:00 PM–5:05 PM | Room 102 (Oral)
Low Latency Privacy Preserving Inference
Alon Brutzkus, Ran Gilad-Bachrach, Oren Elisha
5:10 PM–5:15 PM | Room 103 (Oral)
Provably Efficient RL with Rich Observations via Latent State Decoding
Simon Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudik, John Langford
6:30 PM–9:00 PM | Pacific Ballroom (Poster #63)
On Certifying Non-Uniform Bounds against Adversarial Attacks
Chen Liu, Ryota Tomioka, Volkan Cevher
6:30 PM–9:00 PM | Pacific Ballroom (Poster #66)
Adversarial Examples from Computational Constraints
Sebastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn
6:30 PM–9:00 PM | Pacific Ballroom (Poster #71)
On Learning Invariant Representations for Domain Adaptation
Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoff Gordon
6:30 PM–9:00 PM | Pacific Ballroom (Poster #97)
A Composite Randomized Incremental Gradient Method
Junyu Zhang, Lin Xiao
6:30 PM–9:00 PM | Pacific Ballroom (Poster #101)
Safe Policy Improvement with Baseline Bootstrapping
Romain Laroche, Paul Trichelair, Remi Tachet des Combes
6:30 PM–9:00 PM | Pacific Ballroom (Poster #125)
Contextual Memory Trees
Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro
6:30 PM–9:00 PM | Pacific Ballroom (Poster #160)
Generalized Approximate Survey Propagation for High-Dimensional Estimation
Carlo Lucibello, Luca Saglietti, Yue Lu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #175)
Locally Private Bayesian Inference for Count Models
Aaron Schein, Zhiwei Steven Wu, Alexandra Schofield, Mingyuan Zhou, Hanna Wallach
6:30 PM–9:00 PM | Pacific Ballroom (Poster #176)
Low Latency Privacy Preserving Inference
Alon Brutzkus, Ran Gilad-Bachrach, Oren Elisha
6:30 PM–9:00 PM | Pacific Ballroom (Poster #208)
Provably Efficient RL with Rich Observations via Latent State Decoding
Simon Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudik, John Langford
6:30 PM–9:00 PM | Pacific Ballroom (Poster #216)
Stein Point Markov Chain Monte Carlo
Wilson Ye Chen, Alessandro Barp, Francois-Xavier Briol, Jackson Gorham, Mark Girolami, Lester Mackey, Chris Oates
Wednesday, June 12
11:20 AM–11:25 AM | Room 201 (Oral)
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
Ted Meeds, Geoffrey Roeder, Paul Grant, Andrew Phillips, Neil Dalchau
11:25 AM–11:30 AM | Hall A (Oral)
Are Generative Classifiers More Robust to Adversarial Attacks?
Yingzhen Li, John Bradshaw, Yash Sharma
11:40 AM–12:00 PM | Hall A (Oral)
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Chao Ma, Sebastian Tschiatschek, Konstantina Palla, Jose Hernandez-Lobato, Sebastian Nowozin, Cheng Zhang
2:25 PM–2:30 PM | Room 201 (Oral)
Fast Context Adaptation via Meta-Learning
Luisa Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson
2:35 PM–2:40 PM | Room 103 (Oral)
Orthogonal Random Forest for Causal Inference
Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu
2:40 PM–3:00 PM | Room 101 (Oral)
Variational Implicit Processes
Chao Ma, Yingzhen Li, Jose Hernandez-Lobato
3:05 PM–3:10 PM | Room 104 (Oral)
Riemannian adaptive stochastic gradient algorithms on matrix manifolds
Hiroyuki Kasai, Pratik Kumar Jawanpuria, Bamdev Mishra
4:20 PM–4:25 PM | Grand Ballroom (Oral)
Adaptive Neural Trees
Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, Aditya Nori
4:20 PM–4:25 PM | Room 104 (Oral)
Dead-ends and Secure Exploration in Reinforcement Learning
Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou
4:20 PM–4:25 PM | Room 103 (Oral)
SGD without Replacement: Sharper Rates for General Smooth Convex Functions
Dheeraj Nagaraj, Prateek Jain, Praneeth Netrapalli
4:25 PM–4:30 PM | Grand Ballroom (Oral)
Connectivity-Optimized Representation Learning via Persistent Homology
Christoph Hofer, Roland Kwitt, Marc Niethammer, Mandar Dixit
4:25 PM–4:30 PM | Room 201 (Oral)
Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments
Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabás Póczos
6:30 PM–9:00 PM | Pacific Ballroom (Poster #3)
Are Generative Classifiers More Robust to Adversarial Attacks?
Yingzhen Li, John Bradshaw, Yash Sharma
6:30 PM–9:00 PM | Pacific Ballroom (Poster #6)
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Chao Ma, Sebastian Tschiatschek, Konstantina Palla, Jose Hernandez-Lobato, Sebastian Nowozin, Cheng Zhang
6:30 PM–9:00 PM | Pacific Ballroom (Poster #82)
Adaptive Neural Trees
Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, Aditya Nori
6:30 PM–9:00 PM | Pacific Ballroom (Poster #83)
Connectivity-Optimized Representation Learning via Persistent Homology
Christoph Hofer, Roland Kwitt, Marc Niethammer, Mandar Dixit
6:30 PM–9:00 PM | Pacific Ballroom (Poster #108)
Riemannian adaptive stochastic gradient algorithms on matrix manifolds
Hiroyuki Kasai, Pratik Kumar Jawanpuria, Bamdev Mishra
6:30 PM–9:00 PM | Pacific Ballroom (Poster #112)
Dead-ends and Secure Exploration in Reinforcement Learning
Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou
6:30 PM–9:00 PM | Pacific Ballroom (Poster #195)
Orthogonal Random Forest for Causal Inference
Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #202)
SGD without Replacement: Sharper Rates for General Smooth Convex Functions
Dheeraj Nagaraj, Prateek Jain, Praneeth Netrapalli
6:30 PM–9:00 PM | Pacific Ballroom (Poster #225)
Variational Implicit Processes
Chao Ma, Yingzhen Li, Jose Hernandez-Lobato
6:30 PM–9:00 PM | Pacific Ballroom (Poster #241)
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
Ted Meeds, Geoffrey Roeder, Paul Grant, Andrew Phillips, Neil Dalchau
6:30 PM–9:00 PM | Pacific Ballroom (Poster #252)
Fast Context Adaptation via Meta-Learning
Luisa Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson
6:30 PM–9:00 PM | Pacific Ballroom (Poster #262)
Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments
Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabás Póczos
Thursday, June 13
9:20 AM–9:25 AM | Grand Ballroom (Oral)
Towards a Deep and Unified Understanding of Deep Neural Models in NLP
Chaoyu Guan, Xiting Wang, Quanshi Zhang, Runjin Chen, Di He, Xing Xie
10:05 AM–10:10 AM | Room 201 (Oral)
Almost Unsupervised Text to Speech and Automatic Speech Recognition
Yi Ren, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
10:15 AM–10:30 AM | Room 102 (Oral)
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Alina Beygelzimer, David Pal, Balazs Szorenyi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
11:25 AM–11:30 AM | Room 102 (Oral)
Adaptive Regret of Convex and Smooth Functions
Lijun Zhang, Tie-Yan Liu, Zhi-Hua Zhou
11:30 AM–11:35 AM | Seaside Ballroom (Oral)
Fair Regression: Quantitative Definitions and Reduction-Based Algorithms
Alekh Agarwal, Miroslav Dudik, Zhiwei Steven Wu
11:35 AM–11:40 AM | Grand Ballroom (Oral)
A Convergence Theory for Deep Learning via Over-Parameterization
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
11:35 AM–11:40 AM | Hall B (Oral)
Non-Monotonic Sequential Text Generation
Sean Welleck, Kiante Brantley, Hal Daumé III, Kyunghyun Cho
12:00 PM–12:05 PM | Room 104 (Oral)
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu
12:05 PM–12:10 PM | Room 104 (Oral)
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Limor Gultchin, Genevieve Patterson, Nancy Baym, Nathaniel Swinger, Adam Kalai
12:15 PM–12:20 PM | Hall B (Oral)
Efficient Training of BERT by Progressively Stacking
Linyuan Gong, Di He, Zhuohan Li, Tao Qin, Liwei Wang, Tie-Yan Liu
4:00 PM–4:20 PM | Hall B (Oral)
Decentralized Exploration in Multi-Armed Bandits
Raphael Feraud, Reda Alami, Romain Laroche
4:20 PM–4:25 PM | Hall A (Oral)
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
Ruo-Chun Tzeng, Shan-Hung (Brandon) Wu
4:20 PM–4:25 PM | Hall B (Oral)
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand Negahban
6:30 PM– 9:00 PM | Pacific Ballroom (Poster #22)
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
Ruo-Chun Tzeng, Shan-Hung (Brandon) Wu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #45)
Non-Monotonic Sequential Text Generation
Sean Welleck, Kiante Brantley, Hal Daumé III, Kyunghyun Cho
6:30 PM–9:00 PM | Pacific Ballroom (Poster #50)
Efficient Training of BERT by Progressively Stacking
Linyuan Gong, Di He, Zhuohan Li, Tao Qin, Liwei Wang, Tie-Yan Liu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #51)
Decentralized Exploration in Multi-Armed Bandits
Raphael Feraud, Reda Alami, Romain Laroche
6:30 PM–9:00 PM | Pacific Ballroom (Poster #52)
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand Negahban
6:30 PM–9:00 PM | Pacific Ballroom (Poster #62)
Towards a Deep and Unified Understanding of Deep Neural Models in NLP
Chaoyu Guan, Xiting Wang, Quanshi Zhang, Runjin Chen, Di He, Xing Xie
6:30 PM–9:00 PM | Pacific Ballroom (Poster #75)
A Convergence Theory for Deep Learning via Over-Parameterization
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
6:30 PM–9:00 PM | Pacific Ballroom (Poster #107)
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #108)
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Limor Gultchin, Genevieve Patterson, Nancy Baym, Nathaniel Swinger, Adam Kalai
6:30 PM–9:00 PM | Pacific Ballroom (Poster #132)
Fair Regression: Quantitative Definitions and Reduction-Based Algorithms
Alekh Agarwal, Miroslav Dudik, Zhiwei Steven Wu
6:30 PM–9:00 PM | Pacific Ballroom (Poster #158)
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Alina Beygelzimer, David Pal, Balazs Szorenyi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
6:30 PM–9:00 PM | Pacific Ballroom (Poster #161)
Adaptive Regret of Convex and Smooth Functions
Lijun Zhang, Tie-Yan Liu, Zhi-Hua Zhou
6:30 PM–9:00 PM | Pacific Ballroom (Poster #224)
Almost Unsupervised Text to Speech and Automatic Speech Recognition
Yi Ren, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
Friday, June 14
8:30 AM–6:00 PM | 104A (Workshop)
Climate Change: How Can AI Help?
Co-organizer: Jennifer Chayes
2:00 PM–6:00 PM | Seaside Ballroom (Workshop)
Real-world Sequential Decision Making: Reinforcement Learning and Beyond
Co-organizer: Adith Swaminathan
Saturday, June 15
8:30 AM–6:00 PM | 104B (Workshop)
AI For Social Good
Co-organizer: Lester Mackey
8:30 AM–6:00 PM | Seaside Ballroom (Workshop)
Adaptive and Multitask Learning: Algorithms & Systems
Co-organizer: Rich Caruana
8:30 AM–6:00 PM | 104A (Workshop)
Stein’s Method for Machine Learning and Statistics
Co-organizer: Lester Mackey