# Fairness with Exponential Weights

arXiv: https://arxiv.org/abs/2411.04295 · HTML: https://mlsanity.com/paper/2411.04295/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Builds on (most cited first, 9 of 9)

- [Fairness in Learning: Classic and Contextual Bandits](https://mlsanity.com/paper/1605.07139/) (2016)
- [Achieving Fairness in the Stochastic Multi-armed Bandit Problem](https://mlsanity.com/paper/1907.10516/) (2019)
- [Calibrated Fairness in Bandits](https://mlsanity.com/paper/1707.01875/) (2017)
- [Fairness of Exposure in Stochastic Bandits](https://mlsanity.com/paper/2103.02735/) (2021)
- [A Unifying Framework for Online Optimization with Long-Term Constraints](https://mlsanity.com/paper/2209.07454/) (2022)
- [Equal Opportunity in Online Classification with Partial Feedback](https://mlsanity.com/paper/1902.02242/) (2019)
- [Achieving User-Side Fairness in Contextual Bandits](https://mlsanity.com/paper/2010.12102/) (2020)
- [Nearest Neighbour with Bandit Feedback](https://mlsanity.com/paper/2306.13773/) (2023)
- [Bandits with Abstention under Expert Advice](https://mlsanity.com/paper/2402.14585/) (2024)

## Abstract (arXiv)

Motivated by the need to remove discrimination in certain applications, we develop a meta-algorithm that can convert any efficient implementation of an instance of Hedge (or equivalently, an algorithm for discrete bayesian inference) into an efficient algorithm for the equivalent contextual bandit problem which guarantees exact statistical parity on every trial. Relative to any comparator with statistical parity, the resulting algorithm has the same asymptotic regret bound as running the corresponding instance of Exp4 for each protected characteristic independently. Given that our Hedge instance admits non-stationarity we can handle a varying distribution with which to enforce statistical parity with respect to, which is useful when the true population is unknown and needs to be estimated from the data received so far. Via online-to-batch conversion we can handle the equivalent batch classification problem with exact statistical parity, giving us results that we believe are novel and important in their own right.