Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=WM5895Q1Tpg


Duration: 32:41
1,566 views
41

Jan Stanczuk (University of Cambridge)
https://simons.berkeley.edu/talks/wasserstein-gans-work-because-they-fail
Dynamics and Discretization: PDEs, Sampling, and Optimization



Other Videos By Simons Institute for the Theory of Computing


2021-10-30How to Train Better: Exploiting the Separability of DNNs
2021-10-29A Particle Method for Degenerate Diffusion, and Applications to Robotic Swarming
2021-10-29Deterministic Particle Approximation for Nonlocal Transport Equations
2021-10-29Extending the JKO Scheme Beyond Wasserstein-2 Gradient Flows
2021-10-29Sampling From Wasserstein Barycenter
2021-10-29Consensus Based Sampling
2021-10-29Continuous Time Stochastic Gradient Descent and Flat Minimum Selection
2021-10-29Mean-Field Theory of Two-Layers Neural Networks: Dimension Free Bounds and Example
2021-10-28Archetypal Analysis
2021-10-28Linearised Optimal Transport Distances
2021-10-28Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
2021-10-28Global Well Posedness of Master Equations Mean Field Games
2021-10-27The Singular Set in the Stefan Problem
2021-10-27Optimal Transport With Stopping Times and the Stefan Problem
2021-10-27Foundations of Computing: Donald Knuth | Polylogues
2021-10-27Uniform Convergence Rates for Lipschitz Learning Down to Graph Connectivity
2021-10-27Hessian Informed Mirror Descent With Application in Gradient Flows
2021-10-27Optimal Transport for Learning Chaotic Dynamics via Invariant Measures
2021-10-27Panel on Bosonic Error Correction Codes | Quantum Colloquium
2021-10-27An Error-Corrected Logical Quantum Bit Encoded in Grid States of a Superconducting Cavity
2021-10-27Sampling via Birth-Death Dynamics


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Dynamics and Discretization: PDEs Sampling and Optimization
Jan Stanczuk