Neural Contextual Bandits Under Delayed Feedback Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moghimi, Mohammadali, Jose, Sharu Theresa, Moothedath, Shana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915246166245376
author Moghimi, Mohammadali
Jose, Sharu Theresa
Moothedath, Shana
author_facet Moghimi, Mohammadali
Jose, Sharu Theresa
Moothedath, Shana
contents This paper presents a new algorithm for neural contextual bandits (CBs) that addresses the challenge of delayed reward feedback, where the reward for a chosen action is revealed after a random, unknown delay. This scenario is common in applications such as online recommendation systems and clinical trials, where reward feedback is delayed because the outcomes or results of a user's actions (such as recommendations or treatment responses) take time to manifest and be measured. The proposed algorithm, called Delayed NeuralUCB, uses an upper confidence bound (UCB)-based exploration strategy. Under the assumption of independent and identically distributed sub-exponential reward delays, we derive an upper bound on the cumulative regret over a T-length horizon. We further consider a variant of the algorithm, called Delayed NeuralTS, that uses Thompson Sampling-based exploration. Numerical experiments on real-world datasets, such as MNIST and Mushroom, along with comparisons to benchmark approaches, demonstrate that the proposed algorithms effectively manage varying delays and are well-suited for complex real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Contextual Bandits Under Delayed Feedback Constraints
Moghimi, Mohammadali
Jose, Sharu Theresa
Moothedath, Shana
Machine Learning
This paper presents a new algorithm for neural contextual bandits (CBs) that addresses the challenge of delayed reward feedback, where the reward for a chosen action is revealed after a random, unknown delay. This scenario is common in applications such as online recommendation systems and clinical trials, where reward feedback is delayed because the outcomes or results of a user's actions (such as recommendations or treatment responses) take time to manifest and be measured. The proposed algorithm, called Delayed NeuralUCB, uses an upper confidence bound (UCB)-based exploration strategy. Under the assumption of independent and identically distributed sub-exponential reward delays, we derive an upper bound on the cumulative regret over a T-length horizon. We further consider a variant of the algorithm, called Delayed NeuralTS, that uses Thompson Sampling-based exploration. Numerical experiments on real-world datasets, such as MNIST and Mushroom, along with comparisons to benchmark approaches, demonstrate that the proposed algorithms effectively manage varying delays and are well-suited for complex real-world scenarios.
title Neural Contextual Bandits Under Delayed Feedback Constraints
topic Machine Learning
url https://arxiv.org/abs/2504.12086