## UCB-based Algorithms for Multinomial Logistic Regression Bandits

21 May 2021, 20:48 (modified: 23 Jan 2022, 20:26)NeurIPS 2021 PosterReaders: Everyone
Keywords: Generalized Linear Bandits, Logistic Bandits, Multinomial Logit (MNL), Upper Confidence Bound
TL;DR: We study problems with more than possible outcomes selected by the user and use multinomial logit to model the probability of each possible outcome. We propose an algorithm with sublinear regret with small dependency on problem-dependent constants.
Abstract: Out of the rich family of generalized linear bandits, perhaps the most well studied ones are logistic bandits that are used in problems with binary rewards: for instance, when the learner aims to maximize the profit over a user that can select one of two possible outcomes (e.g., click' vs no-click'). Despite remarkable recent progress and improved algorithms for logistic bandits, existing works do not address practical situations where the number of outcomes that can be selected by the user is larger than two (e.g., click', show me later', never show again', no click'). In this paper, we study such an extension. We use multinomial logit (MNL) to model the probability of each one of $K+1\geq 2$ possible outcomes (+1 stands for the `not click' outcome): we assume that for a learner's action $\mathbf{x}_t$, the user selects one of $K+1\geq 2$ outcomes, say outcome $i$, with a MNL probabilistic model with corresponding unknown parameter $\bar{\boldsymbol{\theta}}_{\ast i}$. Each outcome $i$ is also associated with a revenue parameter $\rho_i$ and the goal is to maximize the expected revenue. For this problem, we present MNL-UCB, an upper confidence bound (UCB)-based algorithm, that achieves regret $\tilde{\mathcal{O}}(dK\sqrt{T})$ with small dependency on problem-dependent constants that can otherwise be arbitrarily large and lead to loose regret bounds. We present numerical simulations that corroborate our theoretical results.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: zip
14 Replies