Separation-Utility Pareto Frontier: An Information-Theoretic Characterization
We study the Pareto frontier (optimal trade-off) between utility and separation, a fairness criterion requiring predictive independence from sensitive attributes conditional on the true outcome. Through an information-theoretic lens, we prove a characterization of the utility-separation Pareto frontier, establish its concavity, and thereby prove the increasing marginal cost of separation in terms of utility. In addition, we characterize the conditions under which this trade-off becomes strict, providing a guide for trade-off selection in practice. Based on the theoretical characterization, we develop an empirical regularizer based on conditional mutual information (CMI) between predictions and sensitive attributes given the true outcome. The CMI regularizer is compatible with any deep model trained via gradient-based optimization and serves as a scalar monitor of residual separation violations, offering tractable guarantees during training. Finally, numerical experiments support our theoretical findings: across COMPAS, UCI Adult, UCI Bank, and CelebA, the proposed method substantially reduces separation violations while matching or exceeding the utility of established baseline methods. This study thus offers a provable, stable, and flexible approach to enforcing separation in deep learning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility
Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interacti…
FairnessPrivacy Preserving$\{\text{PF}\}^2$ES: Parallel Feasible Pareto Frontier Entropy Search for Multi-Objective Bayesian Optimization
We present Parallel Feasible Pareto Frontier Entropy Search ($\{\text{PF}\}^2$ES) -- a novel information-theoretic acquisition function for multi-objective Bayesian optimization supporting unknown constraints and batch q…
Bayesian OptimizationMoSH: Modeling Multi-Objective Tradeoffs with Soft and Hard Bounds
Countless science and engineering applications in multi-objective optimization (MOO) necessitate that decision-makers (DMs) select a Pareto-optimal solution which aligns with their preferences. Evaluating individual solu…
Bayesian OptimizationLarge Language ModelA Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems
Large-scale recommenders encode multi-objective trade-offs by combining multiple predicted outcomes into a single utility score. Although this utility layer can be updated independently of the ranker, weight tuning remai…
Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems
Designing fair algorithmic decision systems requires balancing model performance with fairness toward affected individuals: More fairness might require sacrificing some performance and vice versa, yet the space of possib…
Decision Making