all AI news
Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
Feb. 19, 2024, 5:44 a.m. | Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki
stat.ML updates on arXiv.org arxiv.org
Abstract: In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We propose mean-field Langevin averaged gradient (MFL-AG), a single-loop algorithm that implements gradient descent ascent in the distribution spaces with a novel weighted averaging, and establish average-iterate convergence to the mixed Nash equilibrium. We also study both time and particle discretization regimes and prove a new uniform-in-time propagation of chaos result …
abstract algorithm arxiv distribution dynamics gradient loop math.oc mean minimax novel optimization paper probability spaces stat.ml type updates
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Manager
@ Sanofi | Budapest
Principal Engineer, Data (Hybrid)
@ Homebase | Toronto, Ontario, Canada