Efficient Swap Regret Minimization in Combinatorial Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kontogiannis, Andreas, Pollatos, Vasilis, Mertikopoulos, Panayotis, Panageas, Ioannis
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915768787009536
author Kontogiannis, Andreas
Pollatos, Vasilis
Mertikopoulos, Panayotis
Panageas, Ioannis
author_facet Kontogiannis, Andreas
Pollatos, Vasilis
Mertikopoulos, Panayotis
Panageas, Ioannis
contents This paper addresses the problem of designing efficient no-swap regret algorithms for combinatorial bandits, where the number of actions $N$ is exponentially large in the dimensionality of the problem. In this setting, designing efficient no-swap regret translates to sublinear -- in horizon $T$ -- swap regret with polylogarithmic dependence on $N$. In contrast to the weaker notion of external regret minimization - a problem which is fairly well understood in the literature - achieving no-swap regret with a polylogarithmic dependence on $N$ has remained elusive in combinatorial bandits. Our paper resolves this challenge, by introducing a no-swap-regret learning algorithm with regret that scales polylogarithmically in $N$ and is tight for the class of combinatorial bandits. To ground our results, we also demonstrate how to implement the proposed algorithm efficiently -- that is, with a per-iteration complexity that also scales polylogarithmically in $N$ -- across a wide range of well-studied applications.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02087
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Swap Regret Minimization in Combinatorial Bandits
Kontogiannis, Andreas
Pollatos, Vasilis
Mertikopoulos, Panayotis
Panageas, Ioannis
Machine Learning
This paper addresses the problem of designing efficient no-swap regret algorithms for combinatorial bandits, where the number of actions $N$ is exponentially large in the dimensionality of the problem. In this setting, designing efficient no-swap regret translates to sublinear -- in horizon $T$ -- swap regret with polylogarithmic dependence on $N$. In contrast to the weaker notion of external regret minimization - a problem which is fairly well understood in the literature - achieving no-swap regret with a polylogarithmic dependence on $N$ has remained elusive in combinatorial bandits. Our paper resolves this challenge, by introducing a no-swap-regret learning algorithm with regret that scales polylogarithmically in $N$ and is tight for the class of combinatorial bandits. To ground our results, we also demonstrate how to implement the proposed algorithm efficiently -- that is, with a per-iteration complexity that also scales polylogarithmically in $N$ -- across a wide range of well-studied applications.
title Efficient Swap Regret Minimization in Combinatorial Bandits
topic Machine Learning
url https://arxiv.org/abs/2602.02087