A Geometric and Analytical Perspective on Adversarial Learning Problems

A Geometric and Analytical Perspective on Adversarial Learning Problems

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
69,000
Published on ● Video Link: https://www.youtube.com/watch?v=sVPVkdZu0AQ


Duration: 46:05
564 views
19

Nicolas Garcia Trillos (University of Wisconsin-Madison)
https://simons.berkeley.edu/talks/a-geometric-analytical-perspective
Sampling Algorithms and Geometries on Probability Distributions



Other Videos By Simons Institute for the Theory of Computing


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


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Sampling Algorithms and Geometries on Probability Distributions
Nicolas Garcia Trillos