Unimodal Mono-Partite Matching in a Bandit Setting

Romaric Gaudel, Matthieu Rodet

Abstract

We tackle a new emerging problem, which is finding an optimal monopartite matching in a weighted graph. The semi-bandit version, where a full matching is sampled at each iteration, has been addressed by \cite{ADMA}, creating an algorithm with an expected regret matching $O(\frac{L\log(L)}Δ\log(T))$ with $2L$ players, $T$ iterations and a minimum reward gap $Δ$. We reduce this bound in two steps. First, as in \cite{GRAB} and \cite{UniRank} we use the unimodality property of the expected reward on the appropriate graph to design an algorithm with a regret in $O(L\frac{1}Δ\log(T))$. Secondly, we show that by moving the focus towards the main question `\emph{Is user $i$ better than user $j$?}' this regret becomes $O(L\fracΔ{\tildeΔ^2}\log(T))$, where $\TildeΔ > Δ$ derives from a better way of comparing users. Some experimental results finally show these theoretical results are corroborated in practice.
BibTeX
@misc{gaudel2022unimodal,
  author = {Romaric Gaudel and Matthieu Rodet},
  title = {{Unimodal Mono-Partite Matching in a Bandit Setting}},
  year = {2022},
  eprint = {2208.01511},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.01511},
}

Loading related content...

Figure