Challenges in learning under competition

Speaker: Ana Andreea-Stoica (Research Group Leader - Max Planck Institute for Intelligent Systems, Tuebingen)

Title: Challenges in learning under competition

Abstract: In this talk, I will describe technical challenges in learning under competition, with a case study a game-theoretic model of agents who wish to estimate causal effects in the presence of competition. Many applications of randomized controlled trials involve the presence of multiple treatment administrators—from field experiments to online advertising—that compete for the subjects’ attention. In the face of competition, estimating a causal effect becomes difficult, as the position at which a subject sees a treatment influences their response, and thus the treatment effect. The main technical result establishes an approximation with a tractable objective that maximizes the sample value obtained through strategically allocating budget on subjects. Conceptually, this work successfully combines elements from causal inference and game theory to shed light on the equilibrium behavior of experimentation under competition. We'll discuss societal implications of experimentation derived from our results, from policy evaluation to fairness in marketing campaigns. This work is joint with Vivian Y. Nastl and Moritz Hardt and was presented at ICML'24.