Regulation Games for Trustworthy Machine Learning
CoRR(2024)
摘要
Existing work on trustworthy machine learning (ML) often concentrates on
individual aspects of trust, such as fairness or privacy. Additionally, many
techniques overlook the distinction between those who train ML models and those
responsible for assessing their trustworthiness. To address these issues, we
propose a framework that views trustworthy ML as a multi-objective multi-agent
optimization problem. This naturally lends itself to a game-theoretic
formulation we call regulation games. We illustrate a particular game instance,
the SpecGame in which we model the relationship between an ML model builder and
fairness and privacy regulators. Regulators wish to design penalties that
enforce compliance with their specification, but do not want to discourage
builders from participation. Seeking such socially optimal (i.e., efficient for
all agents) solutions to the game, we introduce ParetoPlay. This novel
equilibrium search algorithm ensures that agents remain on the Pareto frontier
of their objectives and avoids the inefficiencies of other equilibria.
Simulating SpecGame through ParetoPlay can provide policy guidance for ML
Regulation. For instance, we show that for a gender classification application,
regulators can enforce a differential privacy budget that is on average 4.0
lower if they take the initiative to specify their desired guarantee first.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要