Adversarial Bandit over Bandits: Hierarchical Bandits for Online Configuration Management

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Avin, Chen, Lotker, Zvi, Mannor, Shie, Shabat, Gil, Shteingart, Hanan, Yadgar, Roey
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916757225078784
author Avin, Chen
Lotker, Zvi
Mannor, Shie
Shabat, Gil
Shteingart, Hanan
Yadgar, Roey
author_facet Avin, Chen
Lotker, Zvi
Mannor, Shie
Shabat, Gil
Shteingart, Hanan
Yadgar, Roey
contents Motivated by dynamic parameter optimization in finite, but large action (configurations) spaces, this work studies the nonstochastic multi-armed bandit (MAB) problem in metric action spaces with oblivious Lipschitz adversaries. We propose ABoB, a hierarchical Adversarial Bandit over Bandits algorithm that can use state-of-the-art existing "flat" algorithms, but additionally clusters similar configurations to exploit local structures and adapt to changing environments. We prove that in the worst-case scenario, such clustering approach cannot hurt too much and ABoB guarantees a standard worst-case regret bound of $O\left(k^{\frac{1}{2}}T^{\frac{1}{2}}\right)$, where $T$ is the number of rounds and $k$ is the number of arms, matching the traditional flat approach. However, under favorable conditions related to the algorithm properties, clusters properties, and certain Lipschitz conditions, the regret bound can be improved to $O\left(k^{\frac{1}{4}}T^{\frac{1}{2}}\right)$. Simulations and experiments on a real storage system demonstrate that ABoB, using standard algorithms like EXP3 and Tsallis-INF, achieves lower regret and faster convergence than the flat method, up to 50% improvement in known previous setups, nonstochastic and stochastic, as well as in our settings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adversarial Bandit over Bandits: Hierarchical Bandits for Online Configuration Management
Avin, Chen
Lotker, Zvi
Mannor, Shie
Shabat, Gil
Shteingart, Hanan
Yadgar, Roey
Machine Learning
Multiagent Systems
Motivated by dynamic parameter optimization in finite, but large action (configurations) spaces, this work studies the nonstochastic multi-armed bandit (MAB) problem in metric action spaces with oblivious Lipschitz adversaries. We propose ABoB, a hierarchical Adversarial Bandit over Bandits algorithm that can use state-of-the-art existing "flat" algorithms, but additionally clusters similar configurations to exploit local structures and adapt to changing environments. We prove that in the worst-case scenario, such clustering approach cannot hurt too much and ABoB guarantees a standard worst-case regret bound of $O\left(k^{\frac{1}{2}}T^{\frac{1}{2}}\right)$, where $T$ is the number of rounds and $k$ is the number of arms, matching the traditional flat approach. However, under favorable conditions related to the algorithm properties, clusters properties, and certain Lipschitz conditions, the regret bound can be improved to $O\left(k^{\frac{1}{4}}T^{\frac{1}{2}}\right)$. Simulations and experiments on a real storage system demonstrate that ABoB, using standard algorithms like EXP3 and Tsallis-INF, achieves lower regret and faster convergence than the flat method, up to 50% improvement in known previous setups, nonstochastic and stochastic, as well as in our settings.
title Adversarial Bandit over Bandits: Hierarchical Bandits for Online Configuration Management
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2505.19061