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.

翻译：现有关于可信机器学习的研究往往专注于信任的单一维度，例如公平性或隐私性。此外，许多技术忽视了模型训练者与模型可信度评估者之间的角色差异。为解决这些问题，我们提出一个将可信机器学习视为多目标多智能体优化问题的框架。该框架自然引出一种博弈论形式化表述，我们称之为规制博弈。本文阐释了一个具体的博弈实例——规范博弈（SpecGame），其中我们建模了机器学习模型构建者与公平性及隐私规制者之间的关系。规制者希望设计能强制遵守其规范约束的惩罚机制，但又不愿阻碍构建者参与博弈。为寻求此类社会最优（即对所有智能体均有效率）的博弈解，我们引入帕累托博弈（ParetoPlay）。这种新型均衡搜索算法确保各智能体始终处于其目标的帕累托前沿上，并避免了其他均衡的低效率问题。通过帕累托博弈模拟规范博弈，可为机器学习监管提供政策指导。例如，我们证明在性别分类应用中，若规制者主动优先明确其期望保障，则可将差分隐私预算平均降低4.0。