Log In Sign Up

FERMI: Fair Empirical Risk Minimization via Exponential Rényi Mutual Information

by   Andrew Lowy, et al.

In this paper, we propose a new notion of fairness violation, called Exponential Rényi Mutual Information (ERMI). We show that ERMI is a strong fairness violation notion in the sense that it provides upper bound guarantees on existing notions of fairness violation. We then propose the Fair Empirical Risk Minimization via ERMI regularization framework, called FERMI. Whereas most existing in-processing fairness algorithms are deterministic, we provide the first stochastic optimization method with a provable convergence guarantee for solving FERMI. Our stochastic algorithm is amenable to large-scale problems, as we demonstrate experimentally. In addition, we provide a batch (deterministic) algorithm for solving FERMI with the optimal rate of convergence. Both of our algorithms are applicable to problems with multiple (non-binary) sensitive attributes and non-binary targets. Extensive experiments show that FERMI achieves the most favorable tradeoffs between fairness violation and test accuracy across various problem setups compared with state-of-the-art baselines.


page 1

page 2

page 3

page 4


General Fair Empirical Risk Minimization

We tackle the problem of algorithmic fairness, where the goal is to avoi...

Stochastic Differentially Private and Fair Learning

Machine learning models are increasingly used in high-stakes decision-ma...

Tilted Empirical Risk Minimization

Empirical risk minimization (ERM) is typically designed to perform well ...

Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences

Fairness-aware learning is a novel framework for classification tasks. L...

G-IOTA: Fair and confidence aware tangle

This paper proposes strategies to improve the IOTA tangle in terms of re...

On Tilted Losses in Machine Learning: Theory and Applications

Exponential tilting is a technique commonly used in fields such as stati...

FR-Train: A mutual information-based approach to fair and robust training

Trustworthy AI is a critical issue in machine learning where, in additio...