An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gouverneur, Amaury, Rodríguez-Gálvez, Borja, Oechtering, Tobias J., Skoglund, Mikael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912238869151744
author Gouverneur, Amaury
Rodríguez-Gálvez, Borja
Oechtering, Tobias J.
Skoglund, Mikael
author_facet Gouverneur, Amaury
Rodríguez-Gálvez, Borja
Oechtering, Tobias J.
Skoglund, Mikael
contents We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(β\langle a, θ\rangle)/(1+\exp(β\langle a, θ\rangle))$, with slope parameter $β>0$, and where both the action $a\in \mathcal{A}$ and parameter $θ\in \mathcal{O}$ lie within the $d$-dimensional unit ball. Adopting the information-theoretic framework introduced by Russo and Van Roy (2016), we analyze the information ratio, a statistic that quantifies the trade-off between the immediate regret incurred and the information gained about the optimal action. We improve upon previous results by establishing that the information ratio is bounded by $\tfrac{9}{2}dα^{-2}$, where $α$ is a minimax measure of the alignment between the action space $\mathcal{A}$ and the parameter space $\mathcal{O}$, and is independent of $β$. Using this result, we derive a bound of order $O(d/α\sqrt{T \log(βT/d)})$ on the Bayesian expected regret of Thompson Sampling incurred after $T$ time steps. To our knowledge, this is the first regret bound for logistic bandits that depends only logarithmically on $β$ while being independent of the number of actions. In particular, when the action space contains the parameter space, the bound on the expected regret is of order $\tilde{O}(d \sqrt{T})$.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02861
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits
Gouverneur, Amaury
Rodríguez-Gálvez, Borja
Oechtering, Tobias J.
Skoglund, Mikael
Machine Learning
We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(β\langle a, θ\rangle)/(1+\exp(β\langle a, θ\rangle))$, with slope parameter $β>0$, and where both the action $a\in \mathcal{A}$ and parameter $θ\in \mathcal{O}$ lie within the $d$-dimensional unit ball. Adopting the information-theoretic framework introduced by Russo and Van Roy (2016), we analyze the information ratio, a statistic that quantifies the trade-off between the immediate regret incurred and the information gained about the optimal action. We improve upon previous results by establishing that the information ratio is bounded by $\tfrac{9}{2}dα^{-2}$, where $α$ is a minimax measure of the alignment between the action space $\mathcal{A}$ and the parameter space $\mathcal{O}$, and is independent of $β$. Using this result, we derive a bound of order $O(d/α\sqrt{T \log(βT/d)})$ on the Bayesian expected regret of Thompson Sampling incurred after $T$ time steps. To our knowledge, this is the first regret bound for logistic bandits that depends only logarithmically on $β$ while being independent of the number of actions. In particular, when the action space contains the parameter space, the bound on the expected regret is of order $\tilde{O}(d \sqrt{T})$.
title An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits
topic Machine Learning
url https://arxiv.org/abs/2412.02861