ICLR 2020poster19 citations
Smooth markets: A basic mechanism for organizing gradient-based learners
David Balduzzi, Wojciech M. Czarnecki, Tom Anthony, Ian Gemp, Edward Hughes, Joel Leibo, Georgios Piliouras, Thore Graepel
Abstract
With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from game theory show there is little hope of understanding or controlling general n-player games. We therefore introduce smooth markets (SM-games), a class of n-player games with pairwise zero sum interactions. SM-games codify a common design pattern in machine learning that includes some GANs, adversarial training, and other recent algorithms. We show that SM-games are amenable to analysis and optimization using first-order methods.
game theoryoptimizationgradient descentadversarial learning
BibTeX
@inproceedings{
Balduzzi2020Smooth,
title={Smooth markets: A basic mechanism for organizing gradient-based learners},
author={David Balduzzi and Wojciech M. Czarnecki and Tom Anthony and Ian Gemp and Edward Hughes and Joel Leibo and Georgios Piliouras and Thore Graepel},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=B1xMEerYvB}
}