English

Fully Gap-Dependent Bounds for Multinomial Logit Bandit

Machine Learning 2020-11-20 v1

Abstract

We study the multinomial logit (MNL) bandit problem, where at each time step, the seller offers an assortment of size at most KK from a pool of NN items, and the buyer purchases an item from the assortment according to a MNL choice model. The objective is to learn the model parameters and maximize the expected revenue. We present (i) an algorithm that identifies the optimal assortment SS^* within O~(i=1NΔi2)\widetilde{O}(\sum_{i = 1}^N \Delta_i^{-2}) time steps with high probability, and (ii) an algorithm that incurs O(iSKΔi1logT)O(\sum_{i \notin S^*} K\Delta_i^{-1} \log T) regret in TT time steps. To our knowledge, our algorithms are the first to achieve gap-dependent bounds that fully depends on the suboptimality gaps of all items. Our technical contributions include an algorithmic framework that relates the MNL-bandit problem to a variant of the top-KK arm identification problem in multi-armed bandits, a generalized epoch-based offering procedure, and a layer-based adaptive estimation procedure.

Keywords

Cite

@article{arxiv.2011.09998,
  title  = {Fully Gap-Dependent Bounds for Multinomial Logit Bandit},
  author = {Jiaqi Yang},
  journal= {arXiv preprint arXiv:2011.09998},
  year   = {2020}
}

Comments

32 pages

R2 v1 2026-06-23T20:22:41.424Z