Pith. sign in

Learning Equilibria in Matching Markets from Bandit Feedback

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Large-scale, two-sided matching platforms must find market outcomes that align with user preferences while simultaneously learning these preferences from data. Classical notions of stability (Gale and Shapley, 1962; Shapley and Shubik, 1971) are unfortunately of limited value in the learning setting, given that preferences are inherently uncertain and destabilizing while they are being learned. To bridge this gap, we develop a framework and algorithms for learning stable market outcomes under uncertainty. Our primary setting is matching with transferable utilities, where the platform both matches agents and sets monetary transfers between them. We design an incentive-aware learning objective that captures the distance of a market outcome from equilibrium. Using this objective, we analyze the complexity of learning as a function of preference structure, casting learning as a stochastic multi-armed bandit problem. Algorithmically, we show that "optimism in the face of uncertainty," the principle underlying many bandit algorithms, applies to a primal-dual formulation of matching with transfers and leads to near-optimal regret bounds. Our work takes a first step toward elucidating when and how stable matchings arise in large, data-driven marketplaces.

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

Learning in Matching Games with Bandit Feedback

cs.LG · 2025-06-04 · reject · novelty 6.0

A UCB-based algorithm for learning matching equilibria with bandit feedback claims an O~(sqrt(T mk pa)) regret bound, but the proof's final step undercounts the number of pairs matched per round.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning in Matching Games with Bandit Feedback cs.LG · 2025-06-04 · reject · none · ref 26 · internal anchor

    A UCB-based algorithm for learning matching equilibria with bandit feedback claims an O~(sqrt(T mk pa)) regret bound, but the proof's final step undercounts the number of pairs matched per round.