Algorithmic Challenges in Ensuring Fairness at the Time of Decision

• 成果类型: Article; Early Access
• 署名作者: Salem, Tad; Gupta, Swati; Kamble, Vijay
• 署名单位: United States Department of Defense; United States Navy; United States Naval Academy; Massachusetts Institute of Technology (MIT); University of Illinois System; University of Illinois Chicago; University of Illinois Chicago Hospital
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2022.0304
• 发表日期: 2025
• 关键词: price

摘要

Algorithmic decision making in societal contexts, such as retail pricing, loan administration, recommendations on online platforms, etc., can be framed as stochastic optimization under bandit feedback, which typically requires experimentation with different decisions for the sake of learning. Such experimentation often results in perceptions of unfairness among people impacted by these decisions; for instance, there have been several recent lawsuits accusing companies that deploy algorithmic pricing practices of pricegouging. Motivated by the changing legal landscape surrounding algorithmic decision making, we introduce the well-studied fairness notion of envy-freeness within the context of stochastic convex optimization. Our notion requires that upon receiving decisions in the present time, groups do not envy the decisions received by any of the other groups, both in the present as well as the past. This results in a novel trajectory-constrained stochastic optimization problem that renders existing techniques inapplicable. The main technical contribution of this work is to show problem settings where there is no gap in achievable regret (up to logarithmic factors) when envy-freeness is imposed. In particular, in our main result, we develop a near-optimal envy-free algorithm that achieves O( T ) regret for smooth convex functions that satisfy the Polyak-& Lstrok;ojasiewicz (PL) inequality. This algorithm has a coordinate descent structure, in which we carefully leverage gradient information to ensure monotonic sampling along each dimension, while avoiding overshooting the constrained optimum with high probability. The latter aspect critically uses smoothness and the structure of the envy-freeness constraints, whereas the PL inequality allows for sufficient progress toward the optimal solution. We discuss several open questions that arise from this analysis, which may be of independent interest.