kv
March 25, 2023

2023 Workshop on Machine Learning Theory and Foundations

Lieu: Beijing, China

Time                Talk TitlesSpeakers
08:30-08:40OpeningHuishuai Zhang
Session 1
08:40-09:05Faster Neural Network Training, Algorithmically
[video (opens in new tab)]
Jonathan Frankle
09:05-09:30Bayesian Interpolation with Deep Linear Networks
[video (opens in new tab)]
Boris Hanin
09:30-09:55Variational Principles for Mirror Descent and Mirror Langevin Dynamics
[video (opens in new tab)]
Maxim Raginsky
09:55-10:20How Does Sharpness-Aware Minimization Minimize Sharpness?
[video (opens in new tab)]
Zhiyuan Li
10:20-10:35Coffee Break
Session 2
10:35-11:00Analysis of a Toy Case for Emergence
[video (opens in new tab)]
Sebastien Bubeck
11:00-11:25Beyond Neural Scaling Laws: Towards Data Efficient Deep Learning
[video (opens in new tab)]
Surya Ganguli
11:25-11:50Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers
[video (opens in new tab)]
Li Dong
11:50-12:15Flow Straight and Fast: A Simple and Unified Approach to Generative Modeling, Domain Transfer, and Optimal Transport
[video (opens in new tab)]
Qiang Liu
12:15-13:30Lunch Break
Session 3
13:30-13:55Condensation in Deep Learning
[video (opens in new tab)]
Zhiqin Xu
13:55-14:20Adapting to Distribution Shifts: Recent Advances in Importance Weighting Methods
[video (opens in new tab)]
Masashi Sugiyama
14:20-14:45Which Graph Neural Network Can Provably Solve Practical Problems?
[video (opens in new tab)]
Di He
14:45-15:10Contrastive Learning Is Spectral Clustering on Similarity Graph
[video (opens in new tab)]
Yang Yuan
15:10-15:25Coffee Break
Session 4
15:25-15:50On the Theoretical Understanding of MixupKenji Kawaguchi
15:50-16:15Benign Overfitting in Two-layer Convolutional Neural Networks
[video (opens in new tab)]
Yuan Cao
16:15-16:40Environment Invariant Linear Least Squares
[video (opens in new tab)]
Cong Fang