Workshops

Summer 2019

Frontiers of Deep Learning

Jul 15, 2019 to Jul 18, 2019

Return to event »

Monday, July 15th, 2019
8:30 am–8:50 am		Coffee and Check-In
8:50 am–9:00 am		Opening Remarks
9:00 am–9:45 am		Benign Overfitting in Linear Prediction Peter Bartlett (UC Berkeley)
9:45 am–10:30 am		Practical Model-based Algorithms for Reinforcement Learning and Imitation Learning, with Theoretical Analyses Tengyu Ma (Stanford University)
10:30 am–11:00 am		Break
11:00 am–11:45 am		Analyzing Optimization and Generalization in Deep Learning via Trajectories of Gradient Descent Nadav Cohen (Institute for Advanced Study)
11:45 am–12:30 pm		From Classical Statistics to Modern Machine Learning Mikhail Belkin (The Ohio State University)
12:30 pm–2:30 pm		Lunch
2:30 pm–3:15 pm		Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels Yuanzhi Li (Stanford University)
3:15 pm–4:00 pm		Size-free Generalization Bounds for Convolutional Neural Networks Hanie Sedghi (Google Brain)
4:00 pm–5:00 pm		Reception

Tuesday, July 16th, 2019
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization Jason Lee (University of Southern California)
9:45 am–10:30 am		A Primal-dual Analysis of Margin Maximization by Steepest Descent Methods Matus Telgarsky (University of Illinois, Urbana-Champaign)
10:30 am–11:00 am		Break
11:00 am–11:45 am		Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets Rong Ge (Duke University)
11:45 am–12:30 pm		Training on the Test Set and Other Heresies Ben Recht (UC Berkeley)
12:30 pm–2:30 pm		Lunch
2:30 pm–3:15 pm		Computation in Very Wide Neural Networks Yasaman Bahri (Google Brain)
3:15 pm–4:00 pm		Mad Max: Affine Spline Insights into Deep Learning Richard Baraniuk (Rice University)
4:00 pm–4:30 pm		Break
4:30 pm–5:15 pm		Splitting Gradient Descent for Incremental Learning of Neural Architectures Qiang Liu (University of Texas at Austin)

Wednesday, July 17th, 2019
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Provable Robustness Beyond Bound Propagation Zico Kolter (Carnegie Mellon University)
9:45 am–10:30 am		A New Perspective on Adversarial Perturbations Aleksander Madry (MIT)
10:30 am–11:00 am		Break
11:00 am–11:45 am		Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers Jerry Li (Microsoft Research)
11:45 am–12:30 pm		Interpreting Deep Neural Networks (DNNs) Bin Yu (UC Berkeley)
12:30 pm–2:30 pm		Lunch
2:30 pm–3:15 pm		Interpretability - now what? Been Kim (Google Brain)
3:15 pm–4:00 pm		Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples Nicholas Carlini (Google Brain)
4:00 pm–4:30 pm		Break
4:30 pm–5:30 pm		Plenary Discussion: Frontiers of Deep Learning

Thursday, July 18th, 2019
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Robust Deep Learning Under Distribution Shift Zack Lipton (Carnegie Mellon University)
9:45 am–10:30 am		Using Deep Learning for Perception in Autonomous Systems: A Perspective from Control Theory Claire Tomlin (UC Berkeley)
10:30 am–11:00 am		Break
11:00 am–11:45 am		Kernel and Deep Regimes in Overparameterized Learning Suriya Gunasekar (Toyota Technology Institute, Chicago)
11:45 am–12:30 pm		Towards Understanding Transfer Learning with Applications to Medical Imaging Maithra Raghu (Cornell University & Google Brain)
12:30 pm–2:30 pm		Lunch
2:30 pm–3:15 pm		Meta-learning of Optimizers and Update Rules Jascha Sohl-Dickstein (Google Brain)
3:15 pm–4:00 pm		Studying Generalization in Deep Learning via PAC-Bayes Gintare Karolina Dziugaite (Element AI)
4:00 pm–4:15 pm		Break
4:15 pm–4:45 pm		Sample-complexity of Estimating Convolutional and Recurrent Neural Networks Aarti Singh (Carnegie Mellon University)