Merit-based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays

TL;DR

This paper addresses the challenge of designing fair combinatorial semi-bandit algorithms under unrestricted feedback delays, introducing new algorithms with proven sublinear regret and demonstrating their effectiveness through experiments.

Contribution

It introduces novel algorithms for fair combinatorial semi-bandits with unrestricted delays, achieving sublinear regret bounds and handling reward-independent and reward-dependent delays.

Findings

Algorithms achieve sublinear reward regret.

Algorithms achieve sublinear fairness regret.

Effective in synthetic and real-world scenarios.

Abstract

We study the stochastic combinatorial semi-bandit problem with unrestricted feedback delays under merit-based fairness constraints. This is motivated by applications such as crowdsourcing, and online advertising, where immediate feedback is not immediately available and fairness among different choices (or arms) is crucial. We consider two types of unrestricted feedback delays: reward-independent delays where the feedback delays are independent of the rewards, and reward-dependent delays where the feedback delays are correlated with the rewards. Furthermore, we introduce merit-based fairness constraints to ensure a fair selection of the arms. We define the reward regret and the fairness regret and present new bandit algorithms to select arms under unrestricted feedback delays based on their merits. We prove that our algorithms all achieve sublinear expected reward regret and expected fairness regret, with a dependence on the quantiles of the delay distribution. We also conduct extensive experiments using synthetic and real-world data and show that our algorithms can fairly select arms with different feedback delays.