A Mean-Field Theory of Lazy Training in Two-Layer Neural Nets: ...

Channel:

Subscribers:

68,700

Published on September 30, 2021 9:39:26 AM ● Video Link: https://www.youtube.com/watch?v=K9dgAPBTfyU

Duration: 35:26

646 views

Other Videos By Simons Institute for the Theory of Computing

2021-10-02	Adaptive Wavelet Distillation from Neural Networks through Interpretation
2021-10-02	Sliced Normalizing Flow Optimization and Monte Carlo
2021-10-01	MCMC Sampling Around Redistricting and Gerrymandering
2021-10-01	Generative Models for Sampling on Supports Inspired by Observed Data
2021-10-01	When Is the Convergence Time of Langevin Algorithms Dimension Independent: ...
2021-10-01	High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
2021-10-01	Minimax Mixing Time of the Metropolis-Adjusted Langevin Algorithm for Log-Concave Sampling
2021-10-01	Quantitative Convergence Analysis of Hypocoercive Sampling Dynamics
2021-09-30	Sampling Convex Bodies: A Status Report
2021-09-30	Kernel Stein Discrepancy Descent
2021-09-30	A Mean-Field Theory of Lazy Training in Two-Layer Neural Nets: ...
2021-09-30	A Blob Method for Diffusion and Applications to Sampling and Two Layer Neural Networks
2021-09-29	A Geometric and Analytical Perspective on Adversarial Learning Problems
2021-09-29	Blackwell Institute Students \| Polylogues
2021-09-29	Current and Future Applications of Sampling Algorithms in Modelling Biochemical Networks
2021-09-29	Random Coordinate Descent and Langevin Monte Carlo
2021-09-29	Algorithms for Sampling Convex Bodies
2021-09-29	Structured Logconcave Sampling with a Restricted Gaussian Oracle
2021-09-29	Primal--Dual Optimization and Application to Sampling
2021-09-29	Non-Equilibrium Sampling
2021-09-28	On Langevin Monte Carlo for Log-Concave Densities

Tags:

Simons Institute

theoretical computer science

UC Berkeley

Computer Science

Theory of Computation

Theory of Computing

Sampling Algorithms and Geometries on Probability Distributions

Belinda Tzen