Continuous Time Stochastic Gradient Descent and Flat Minimum Selection

Channel:

Subscribers:

68,700

Published on October 29, 2021 7:24:18 AM ● Video Link: https://www.youtube.com/watch?v=ZTCrgE3LTrk

Duration: 43:36

393 views

Other Videos By Simons Institute for the Theory of Computing

2021-10-30	Density Control of Interacting Agent Systems
2021-10-30	Discrete-To-Continuum Limits of Dynamical Optimal Transport Problems
2021-10-30	Learning Interaction Kernels in Stochastic Systems of...
2021-10-30	Mirror Descent Algorithms for Minimizing Interacting Free Energy
2021-10-30	How to Train Better: Exploiting the Separability of DNNs
2021-10-29	A Particle Method for Degenerate Diffusion, and Applications to Robotic Swarming
2021-10-29	Deterministic Particle Approximation for Nonlocal Transport Equations
2021-10-29	Extending the JKO Scheme Beyond Wasserstein-2 Gradient Flows
2021-10-29	Sampling From Wasserstein Barycenter
2021-10-29	Consensus Based Sampling
2021-10-29	Continuous Time Stochastic Gradient Descent and Flat Minimum Selection
2021-10-29	Mean-Field Theory of Two-Layers Neural Networks: Dimension Free Bounds and Example
2021-10-28	Archetypal Analysis
2021-10-28	Linearised Optimal Transport Distances
2021-10-28	Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
2021-10-28	Global Well Posedness of Master Equations Mean Field Games
2021-10-27	The Singular Set in the Stefan Problem
2021-10-27	Optimal Transport With Stopping Times and the Stefan Problem
2021-10-27	Foundations of Computing: Donald Knuth \| Polylogues
2021-10-27	Uniform Convergence Rates for Lipschitz Learning Down to Graph Connectivity
2021-10-27	Hessian Informed Mirror Descent With Application in Gradient Flows

Tags:

Simons Institute

theoretical computer science

UC Berkeley

Computer Science

Theory of Computation

Theory of Computing

Dynamics and Discretization: PDEs Sampling and Optimization

Stephan Wojtowytsch