The Foundations of AI Seminar Series is dedicated to topics of interest in artificial intelligence, machine learning, both empirically and theoretically, as well as related areas. Our goal is for these meetings to serve as a forum for discussions and quick dissemination of results. We invite anyone interested in the latest advancements in AI/ML to join us!
Multi-objective optimization with societal considerations: a study of RCTs in the presence of competing treatments
Speaker: Ana-Andreea Stoica (Tübingen, Baden-Württemberg, Germany) Date: 12-11-2024, 2pm-3pm (BST) Location: Zeeman building, MS.03, University of Warwick, Coventry, UK
Abstract
My work focuses on solving multi-objective optimization problems in the context of resource allocation problems, where societal considerations such as fairness or incentives are at play. In this talk, I will focus on a particular study of treatment estimation under competition, published at ICML’24. In many applications of randomized controlled trials, users are subject to multiple experiments at the same time (e.g. seeing multiple ads on online platforms). For an experimenter, estimating a causal effect becomes difficult under competition from other experiments, as the position at which a user sees a treatment influences their response. In this paper, we build a game-theoretic model of agents who wish to estimate causal effects in the presence of competition, through a bidding system and a utility function that minimizes estimation error. Our main technical result establishes an approximation with a tractable objective that maximizes the sample value obtained through strategically allocating budget on subjects. This allows us to find an equilibrium in our model under broad conditions. Conceptually, our work combines elements from causal inference and game theory to shed light on the equilibrium behavior of experimentation under competition. This is joint work with Vivian Y. Nastl and Moritz Hardt.
About Ana-Andreea Stoica
Ana-Andreea Stoica is a Research Group Leader in the Social Foundations of Computation group at the Max Planck Institute for Intelligent Systems, Tuebingen. Her work focuses on multi-objective optimization problems with societal considerations, from algorithmic design with fairness considerations to evaluating resource-allocation systems with equity and incentive alignment. Ana is particularly interested in studying the effect of algorithms on people’s sense of community and access to information and opportunities. Ana holds a Ph.D. from Columbia University and a B.A. in Mathematics from Princeton University. Since 2019, she has been co-organizing the EAAMO Bridges initiative and is a co-founder of ACM conference series on Equity and Access in Algorithms, Mechanisms, and Optimization.