Saved in:
Bibliographic Details
Main Author: Zhang, Di
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08908
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909833829023744
author Zhang, Di
author_facet Zhang, Di
contents The stochastic multi-armed bandit (MAB) problem is one of the most fundamental models in sequential decision-making, with the core challenge being the trade-off between exploration and exploitation. Although algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling, along with their regret theories, are well-established, existing analyses primarily operate from a time-domain and cumulative regret perspective, struggling to characterize the dynamic nature of the learning process. This paper proposes a novel frequency-domain analysis framework, reformulating the bandit process as a signal processing problem. Within this framework, the reward estimate of each arm is viewed as a spectral component, with its uncertainty corresponding to the component's frequency, and the bandit algorithm is interpreted as an adaptive filter. We construct a formal Frequency-Domain Bandit Model and prove the main theorem: the confidence bound term in the UCB algorithm is equivalent in the frequency domain to a time-varying gain applied to uncertain spectral components, a gain inversely proportional to the square root of the visit count. Based on this, we further derive finite-time dynamic bounds concerning the exploration rate decay. This theory not only provides a novel and intuitive physical interpretation for classical algorithms but also lays a rigorous theoretical foundation for designing next-generation algorithms with adaptive parameter adjustment.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08908
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Frequency-Domain Analysis of the Multi-Armed Bandit Problem: A New Perspective on the Exploration-Exploitation Trade-off
Zhang, Di
Machine Learning
Artificial Intelligence
Information Theory
Optimization and Control
68T05, 62L05, 94A12
I.2.6; G.3
The stochastic multi-armed bandit (MAB) problem is one of the most fundamental models in sequential decision-making, with the core challenge being the trade-off between exploration and exploitation. Although algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling, along with their regret theories, are well-established, existing analyses primarily operate from a time-domain and cumulative regret perspective, struggling to characterize the dynamic nature of the learning process. This paper proposes a novel frequency-domain analysis framework, reformulating the bandit process as a signal processing problem. Within this framework, the reward estimate of each arm is viewed as a spectral component, with its uncertainty corresponding to the component's frequency, and the bandit algorithm is interpreted as an adaptive filter. We construct a formal Frequency-Domain Bandit Model and prove the main theorem: the confidence bound term in the UCB algorithm is equivalent in the frequency domain to a time-varying gain applied to uncertain spectral components, a gain inversely proportional to the square root of the visit count. Based on this, we further derive finite-time dynamic bounds concerning the exploration rate decay. This theory not only provides a novel and intuitive physical interpretation for classical algorithms but also lays a rigorous theoretical foundation for designing next-generation algorithms with adaptive parameter adjustment.
title A Frequency-Domain Analysis of the Multi-Armed Bandit Problem: A New Perspective on the Exploration-Exploitation Trade-off
topic Machine Learning
Artificial Intelligence
Information Theory
Optimization and Control
68T05, 62L05, 94A12
I.2.6; G.3
url https://arxiv.org/abs/2510.08908