Saved in:
Bibliographic Details
Main Author: Basu, Soumya
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.15926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913901135790080
author Basu, Soumya
author_facet Basu, Soumya
contents We study bandit learning in matching markets with two-sided reward uncertainty, extending prior research primarily focused on single-sided uncertainty. Leveraging the concept of `super-stability' from Irving (1994), we demonstrate the advantage of the Extended Gale-Shapley (GS) algorithm over the standard GS algorithm in achieving true stable matchings under incomplete information. By employing the Extended GS algorithm, our centralized algorithm attains a logarithmic pessimal stable regret dependent on an instance-dependent admissible gap parameter. This algorithm is further adapted to a decentralized setting with a constant regret increase. Finally, we establish a novel centralized instance-dependent lower bound for binary stable regret, elucidating the roles of the admissible gap and super-stable matching in characterizing the complexity of stable matching with bandit feedback.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Competing Bandits in Matching Markets via Super Stability
Basu, Soumya
Machine Learning
Information Theory
We study bandit learning in matching markets with two-sided reward uncertainty, extending prior research primarily focused on single-sided uncertainty. Leveraging the concept of `super-stability' from Irving (1994), we demonstrate the advantage of the Extended Gale-Shapley (GS) algorithm over the standard GS algorithm in achieving true stable matchings under incomplete information. By employing the Extended GS algorithm, our centralized algorithm attains a logarithmic pessimal stable regret dependent on an instance-dependent admissible gap parameter. This algorithm is further adapted to a decentralized setting with a constant regret increase. Finally, we establish a novel centralized instance-dependent lower bound for binary stable regret, elucidating the roles of the admissible gap and super-stable matching in characterizing the complexity of stable matching with bandit feedback.
title Competing Bandits in Matching Markets via Super Stability
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2506.15926