Learning in Stochastic Monotone Games with Decision-Dependent Data
Abstract
Learning problems commonly exhibit an interesting feedback mechanism wherein the population data reacts to competing decision makers’ actions. This paper formulates a new game theoretic framework for this phenomenon, called multi-player performative prediction. We establish transparent sufficient conditions for strong monotonicity of the game and use them to develop algorithms for finding Nash equilibria. We investigate derivative free methods and adaptive gradient algorithms wherein each player alternates between learning a parametric description of their distribution and gradient steps on the empirical risk. Synthetic and semi-synthetic numerical experiments illustrate the results.
Cite
Text
Narang et al. "Learning in Stochastic Monotone Games with Decision-Dependent Data." Artificial Intelligence and Statistics, 2022.Markdown
[Narang et al. "Learning in Stochastic Monotone Games with Decision-Dependent Data." Artificial Intelligence and Statistics, 2022.](https://mlanthology.org/aistats/2022/narang2022aistats-learning/)BibTeX
@inproceedings{narang2022aistats-learning,
title = {{Learning in Stochastic Monotone Games with Decision-Dependent Data}},
author = {Narang, Adhyyan and Faulkner, Evan and Drusvyatskiy, Dmitriy and Fazel, Maryam and Ratliff, Lillian},
booktitle = {Artificial Intelligence and Statistics},
year = {2022},
pages = {5891-5912},
volume = {151},
url = {https://mlanthology.org/aistats/2022/narang2022aistats-learning/}
}