Smooth Markets: A Basic Mechanism for Organizing Gradient-Based Learners
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.
Cite
Text
Balduzzi et al. "Smooth Markets: A Basic Mechanism for Organizing Gradient-Based Learners." International Conference on Learning Representations, 2020.Markdown
[Balduzzi et al. "Smooth Markets: A Basic Mechanism for Organizing Gradient-Based Learners." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/balduzzi2020iclr-smooth/)BibTeX
@inproceedings{balduzzi2020iclr-smooth,
title = {{Smooth Markets: A Basic Mechanism for Organizing Gradient-Based Learners}},
author = {Balduzzi, David and Czarnecki, Wojciech M and Anthony, Thomas W and Gemp, Ian M and Hughes, Edward and Leibo, Joel Z and Piliouras, Georgios and Graepel, Thore},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/balduzzi2020iclr-smooth/}
}