Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games
Jul 12, 2020
Speakers
Zhengyuan Zhou
Speaker · 0 followers
Panayotis Mertikopoulos
Speaker · 0 followers
Michael I. Jordan
Speaker · 13 followers
Darren Lin
Speaker · 0 followers
About
In this paper, we consider multi-agent learning via online gradient descent in a class of games called λ-cocoercive games, a fairly broad class of games that admits many Nash equilibria and that properly includes strongly monotone games. We characterize the finite-time last-iterate convergence rate for joint OGD learning on λ-cocoercive games; further, building on this result, we develop a fully adaptive OGD learning algorithm that does not require any knowledge of the problem parameter (e.g. cocoercive constant λ) and show, via a novel double-stopping time technique, that this adaptive algorithm achieves the same finite-time last-iterate convergence rate as its non-adaptive counterpart. Subsequently, we extend OGD learning to the noisy gradient feedback case and establish last-iterate convergence results–first qualitative almost sure convergence, then quantitative finite-time convergence rates– all under non-decreasing step-sizes. To the best of our knowledge, we provide the first set of results that fill in several gaps of the existing multi-agent online learning literature, where three aspects–finite-time convergence rates, non-decreasing step-sizes, and fully adaptive algorithms have not been previously unexplored.In this paper, we consider multi-agent learning via online gradient descent in a class of games called λ-cocoercive games, a fairly broad class of games that admits many Nash equilibria and that properly includes strongly monotone games. We characterize the finite-time last-iterate convergence rate for joint OGD learning on λ-cocoercive games; further, building on this result, we develop a fully adaptive OGD learning algorithm that does not require any knowledge of the problem parameter (e.g. co…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
DropNet: Reducing Neural Network Complexity via Iterative Pruning
Watch later
Mehul Motani, …
Optimal Differential Privacy Composition for Exponential Mechanisms
Watch later
Jinshuo Dong, …
Two Routes to Scalable Credit Assignment without Weight Symmetry
Watch later
Daniel Kunin, …
Topological Autoencoders
Watch later
Michael Moor, …
Variational Bayesian Quantization
Watch later
Yibo Yang, …
Submodular Optimization: From Discrete to Continuous and Back - Part I
Watch later
Amin Karbasi, …