Below are the approved videos and slides from the Bridging Mathematical Optimization, Information Theory, and Data Science Conference.
Peter Bartlett (UC Berkeley) - Optimization and Generalization Properties of Deep Neural Networks
Sebastien Bubeck (Microsoft Research) - Metrical Task Systems on Trees
Yuejie Chi (Carnegie Melon University) - Geometry and Regularization in Nonconvex Statistical Estimation
Alex Dimakis (University of Texas at Auston) - Gans for Compressed Sensing and Adversarial Defense
Donald Goldfarb (Columbia University) - ADMM for Multiaffine Constrained Optimization: Theory and Applications
Alfred Hero (University of Michigan) - Rate-Optimal Meta-Learning
Andrea Montanari (Stanford University) - A Mean Field View of the Landscape of Two-Layers Neural Networks
Arkadi Nemirovski (Georgia Tech) - Tight Semidefinite Relaxations and Statistical Estimation
Robert Nowak (University of Wisconsin) - Outranked: Exploiting Nonlinear Algebraic Structure in Matrix Recovery Problems
Alex Shapiro (Georgia Tech) - Matrix Completion with Deterministic Pattern
Weijie Su (University of Pennsylvania) - HiGrad: Statistical Inference for Online Learning and Stochastic Approximation
David Tse (Stanford University) - Understanding Generative Adversarial Networks
Yihong Wu (Yale University) - Recovering a Hidden Hamiltonian Cycle via Linear Programming
Anru Zhang (University of Wisconsin) - Sparse and Low-Rank Tensor Estimation via Cubic Sketchings