License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ICALP.2022.2
URN: urn:nbn:de:0030-drops-163431
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2022/16343/
Go to the corresponding LIPIcs Volume Portal

Daskalakis, Constantinos

Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning (Invited Talk)

pdf-format:
LIPIcs-ICALP-2022-2.pdf (0.4 MB)

Abstract

Machine Learning has recently made significant advances in challenges such as speech and image recognition, automatic translation, and text generation, much of that progress being fueled by the success of gradient descent-based optimization methods in computing local optima of non-convex objectives. From robustifying machine learning models against adversarial attacks to causal inference, training generative models, multi-robot interactions, and learning in strategic environments, many outstanding challenges in Machine Learning lie at its interface with Game Theory. On this front, however, gradient-descent based optimization methods have been less successful. Here, the role of single-objective optimization is played by equilibrium computation, but gradient-descent based methods commonly fail to find equilibria, and even computing local approximate equilibria has remained daunting. We shed light on these challenges through a combination of learning-theoretic, complexity-theoretic, game-theoretic and topological techniques, presenting obstacles and opportunities for Machine Learning and Game Theory going forward. I will assume no Deep Learning background for this talk and present results from joint works with S. Skoulakis and M. Zampetakis [Daskalakis et al., 2021] as well as with N. Golowich and K. Zhang [Daskalakis et al., 2022].

BibTeX - Entry

@InProceedings{daskalakis:LIPIcs.ICALP.2022.2,
  author =	{Daskalakis, Constantinos},
  title =	{{Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning}},
  booktitle =	{49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)},
  pages =	{2:1--2:1},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-235-8},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{229},
  editor =	{Boja\'{n}czyk, Miko{\l}aj and Merelli, Emanuela and Woodruff, David P.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16343},
  URN =		{urn:nbn:de:0030-drops-163431},
  doi =		{10.4230/LIPIcs.ICALP.2022.2},
  annote =	{Keywords: Deep Learning, Multi-Agent (Reinforcement) Learning, Game Theory, Nonconvex Optimization, PPAD}
}

Keywords: Deep Learning, Multi-Agent (Reinforcement) Learning, Game Theory, Nonconvex Optimization, PPAD
Collection: 49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)
Issue Date: 2022
Date of publication: 28.06.2022

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI