Implicit Regularization in Nonconvex Statistical Estimation

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=DMvxqVdqwZI


Duration: 28:46
1,725 views
23

Yuxin Chen, Princeton University
https://simons.berkeley.edu/talks/yuxin-chen-11-29-17
Optimization, Statistics and Uncertainty



Other Videos By Simons Institute for the Theory of Computing


2017-12-01Stability and Convergence Trade-Off of Iterative Optimization Algorithms
2017-12-01Compositional Properties of Statistical Procedures: An Information-Theoretic View
2017-11-30Sampling Algorithms for Combinatorial Pure Exploration
2017-11-30The Power and Limitations of Kernel Learning
2017-11-30Optimization's Untold Gift to Learning: Implicit Regularization
2017-11-30Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe
2017-11-30On Approximation Guarantees for Greedy Low Rank Optimization
2017-11-30Graph Powering
2017-11-29Low-rank Matrix Completion: Adaptive Sampling Can Help When, How?
2017-11-29Fireside Chat with Simons Institute Director Dick Karp
2017-11-29Implicit Regularization in Nonconvex Statistical Estimation
2017-11-29A Few Connections Between Optimization and Probability
2017-11-29An Instability in Variational Methods for Learning Topic Models
2017-11-28Distributional Robustness, Learning, and Empirical Likelihood
2017-11-28The Convergence of Hamiltonian Monte Carlo
2017-11-28Preventing Overfitting in Adaptive Data Analysis via Stability
2017-11-28Algorithmic Stability for Interactive Data Analysis
2017-11-28Learning One-hidden-layer Neural Networks with Landscape Design
2017-11-28Regularized Nonlinear Acceleration
2017-11-28Data Driven Optimization Models and Algorithms
2017-11-28Michael Cohen and Directed Laplacians


Tags:
Yuxin Chen
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Optimization Statistics and Uncertainty