–
Coffee and Check-In
–
Opening Remarks
–
Benign Overfitting in Linear Prediction
Peter Bartlett (Simons Institute, UC Berkeley)
–
Practical Model-based Algorithms for Reinforcement Learning and Imitation Learning, with Theoretical Analyses
Tengyu Ma (Facebook AI Research)
–
Break
–
Analyzing Optimization and Generalization in Deep Learning via Trajectories of Gradient Descent
Nadav Cohen (Institute for Advanced Study)
–
From Classical Statistics to Modern Machine Learning
Misha Belkin (UCSD)
–
Lunch
–
Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels
Yuanzhi Li (Stanford University)
–
Size-free Generalization Bounds for Convolutional Neural Networks
Hanie Sedghi (Google Brain)
–
Reception
–
Coffee and Check-In
–
On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization
Jason Lee (University of Southern California)
–
A Primal-dual Analysis of Margin Maximization by Steepest Descent Methods
Matus Telgarsky (New York University)
–
Break
–
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rong Ge (Duke University)
–
Training on the Test Set and Other Heresies
Benjamin Recht (UC Berkeley)
–
Lunch
–
Computation in Very Wide Neural Networks
Yasaman Bahri (Google Brain)
–
Mad Max: Affine Spline Insights into Deep Learning
Richard Baraniuk (Rice University)
–
Break
–
Splitting Gradient Descent for Incremental Learning of Neural Architectures
Qiang Liu (University of Texas at Austin)
–
Coffee and Check-In
–
Provable Robustness Beyond Bound Propagation
Zico Kolter (Carnegie Mellon University)
–
A New Perspective on Adversarial Perturbations
Aleksander Mądry (Massachusetts Institute of Technology)
–
Break
–
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Jerry Li (Microsoft Research)
–
Interpreting Deep Neural Networks (DNNs)
Bin Yu (UC Berkeley)
–
Lunch
–
Interpretability - now what?
Been Kim (Google Brain)
–
Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples
Nicholas Carlini (Google Brain)
–
Break
–
Plenary Discussion: Frontiers of Deep Learning
–
Coffee and Check-In
–
Robust Deep Learning Under Distribution Shift
Zack Lipton (Carnegie Mellon University)
–
Using Deep Learning for Perception in Autonomous Systems: A Perspective from Control Theory
Claire Tomlin (UC Berkeley)
–
Break
–
Kernel and Deep Regimes in Overparameterized Learning
Suriya Gunasekar (Toyota Technology Institute, Chicago)
–
Towards Understanding Transfer Learning with Applications to Medical Imaging
Maithra Raghu (Cornell University and Google Inc.)
–
Lunch
–
Meta-learning of Optimizers and Update Rules
Jascha Sohl-Dickstein (Google Brain)
–
Studying Generalization in Deep Learning via PAC-Bayes
Gintare Karolina Dziugaite (Element AI)
–
Break
–
Sample-complexity of Estimating Convolutional and Recurrent Neural Networks
Aarti Singh (Carnegie Mellon University)