Active Learning for Fair and Stable Online Allocations

TL;DR

This paper introduces an active learning method for online resource allocation that efficiently uses limited agent feedback to achieve fair and stable outcomes, with proven regret bounds.

Contribution

It proposes algorithms that adaptively select informative feedback to optimize fairness and stability in online allocations with limited agent input.

Findings

Regret bounds are sub-linear in time periods.

Efficient outcomes achieved with limited feedback.

Adaptive feedback selection improves decision-making.

Abstract

We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of the online resource allocation process. Despite this restriction, our proposed algorithms provide regret bounds that are sub-linear in number of time-periods for various measures that include fairness metrics commonly used in resource allocation problems and stability considerations in matching mechanisms. The key insight of our algorithms lies in adaptively identifying the most informative feedback using dueling upper and lower confidence bounds. With this strategy, we show that efficient decision-making does not require extensive feedback and produces efficient outcomes for a variety of problem classes.