Group Meritocratic Fairness in Linear Contextual Bandits

by   Riccardo Grazzi, et al.

We study the linear contextual bandit problem where an agent has to select one candidate from a pool and each candidate belongs to a sensitive group. In this setting, candidates' rewards may not be directly comparable between groups, for example when the agent is an employer hiring candidates from different ethnic groups and some groups have a lower reward due to discriminatory bias and/or social injustice. We propose a notion of fairness that states that the agent's policy is fair when it selects a candidate with highest relative rank, which measures how good the reward is when compared to candidates from the same group. This is a very strong notion of fairness, since the relative rank is not directly observed by the agent and depends on the underlying reward model and on the distribution of rewards. Thus we study the problem of learning a policy which approximates a fair policy under the condition that the contexts are independent between groups and the distribution of rewards of each group is absolutely continuous. In particular, we design a greedy policy which at each round constructs a ridge regression estimator from the observed context-reward pairs, and then computes an estimate of the relative rank of each candidate using the empirical cumulative distribution function. We prove that the greedy policy achieves, after T rounds, up to log factors and with high probability, a fair pseudo-regret of order √(dT), where d is the dimension of the context vectors. The policy also satisfies demographic parity at each round when averaged over all possible information available before the selection. We finally show with a proof of concept simulation that our policy achieves sub-linear fair pseudo-regret also in practice.


page 1

page 2

page 3

page 4


Context-lumpable stochastic bandits

We consider a contextual bandit problem with S contexts and A actions. I...

Contextual bandits with concave rewards, and an application to fair ranking

We consider Contextual Bandits with Concave Rewards (CBCR), a multi-obje...

Doubly Fair Dynamic Pricing

We study the problem of online dynamic pricing with two types of fairnes...

Fair Exploration via Axiomatic Bargaining

Motivated by the consideration of fairly sharing the cost of exploration...

Fairness in Selection Problems with Strategic Candidates

To better understand discriminations and the effect of affirmative actio...

A Unified Approach to Fair Online Learning via Blackwell Approachability

We provide a setting and a general approach to fair online learning with...

Affirmative Action Policies for Top-k Candidates Selection, With an Application to the Design of Policies for University Admissions

We consider the problem of designing affirmative action policies for sel...

Please sign up or login with your details

Forgot password? Click here to reset