Log In Sign Up

Multiplayer Performative Prediction: Learning in Decision-Dependent Games

by   Adhyyan Narang, et al.

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 focus on two distinct solution concepts, namely (i) performatively stable equilibria and (ii) Nash equilibria of the game. The latter equilibria are arguably more informative, but can be found efficiently only when the game is monotone. We show that under mild assumptions, the performatively stable equilibria can be found efficiently by a variety of algorithms, including repeated retraining and repeated (stochastic) gradient play. We then 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.


page 26

page 28


Actor-Critic Algorithms for Learning Nash Equilibria in N-player General-Sum Games

We consider the problem of finding stationary Nash equilibria (NE) in a ...

Non-Myopic Learning in Repeated Stochastic Games

This paper addresses learning in repeated stochastic games (RSGs) played...

Finding Nash Equilibria of Two-Player Games

This paper is an exposition of algorithms for finding one or all equilib...

On Game-Theoretic Risk Management (Part Three) - Modeling and Applications

The game-theoretic risk management framework put forth in the precursor ...

Weak Monotone Comparative Statics

We develop a theory of monotone comparative statics based on weak set or...

Which Echo Chamber? Regions of Attraction in Learning with Decision-Dependent Distributions

As data-driven methods are deployed in real-world settings, the processe...

Individual Altruism Cannot Overcome Congestion Effects in a Global Pandemic Game

A key challenge in responding to public health crises such as COVID-19 i...