Nearly Minimax Optimal Regret for Multinomial Logistic Bandit

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Joongkyu, Oh, Min-hwan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918161797873664
author Lee, Joongkyu
Oh, Min-hwan
author_facet Lee, Joongkyu
Oh, Min-hwan
contents In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a significant discrepancy between lower and upper regret bounds, particularly regarding the maximum assortment size $K$. Additionally, the variation in reward structures between these bounds complicates the quest for optimality. Under uniform rewards, where all items have the same expected reward, we establish a regret lower bound of $Ω(d\sqrt{T/K})$ and propose a constant-time algorithm, OFU-MNL+, that achieves a matching upper bound of $\tilde{O}(d\sqrt{T/K})$. We also provide instance-dependent minimax regret bounds under uniform rewards. Under non-uniform rewards, we prove a lower bound of $Ω(d\sqrt{T})$ and an upper bound of $\tilde{O}(d\sqrt{T})$, also achievable by OFU-MNL+. Our empirical studies support these theoretical findings. To the best of our knowledge, this is the first work in the contextual MNL bandit literature to prove minimax optimality -- for either uniform or non-uniform reward setting -- and to propose a computationally efficient algorithm that achieves this optimality up to logarithmic factors.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Lee, Joongkyu
Oh, Min-hwan
Machine Learning
In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a significant discrepancy between lower and upper regret bounds, particularly regarding the maximum assortment size $K$. Additionally, the variation in reward structures between these bounds complicates the quest for optimality. Under uniform rewards, where all items have the same expected reward, we establish a regret lower bound of $Ω(d\sqrt{T/K})$ and propose a constant-time algorithm, OFU-MNL+, that achieves a matching upper bound of $\tilde{O}(d\sqrt{T/K})$. We also provide instance-dependent minimax regret bounds under uniform rewards. Under non-uniform rewards, we prove a lower bound of $Ω(d\sqrt{T})$ and an upper bound of $\tilde{O}(d\sqrt{T})$, also achievable by OFU-MNL+. Our empirical studies support these theoretical findings. To the best of our knowledge, this is the first work in the contextual MNL bandit literature to prove minimax optimality -- for either uniform or non-uniform reward setting -- and to propose a computationally efficient algorithm that achieves this optimality up to logarithmic factors.
title Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
topic Machine Learning
url https://arxiv.org/abs/2405.09831