Cascading Bandits Robust to Adversarial Corruptions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xie, Jize, Chen, Cheng, Wang, Zhiyong, Li, Shuai
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909489222909952
author Xie, Jize
Chen, Cheng
Wang, Zhiyong
Li, Shuai
author_facet Xie, Jize
Chen, Cheng
Wang, Zhiyong
Li, Shuai
contents Online learning to rank sequentially recommends a small list of items to users from a large candidate set and receives the users' click feedback. In many real-world scenarios, users browse the recommended list in order and click the first attractive item without checking the rest. Such behaviors are usually formulated as the cascade model. Many recent works study algorithms for cascading bandits, an online learning to rank framework in the cascade model. However, the performance of existing methods may drop significantly if part of the user feedback is adversarially corrupted (e.g., click fraud). In this work, we study how to resist adversarial corruptions in cascading bandits. We first formulate the ``\textit{Cascading Bandits with Adversarial Corruptions}" (CBAC) problem, which assumes that there is an adaptive adversary that may manipulate the user feedback. Then we propose two robust algorithms for this problem, which assume the corruption level is known and agnostic, respectively. We show that both algorithms can achieve logarithmic regret when the algorithm is not under attack, and the regret increases linearly with the corruption level. The experimental results also verify the robustness of our methods.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08077
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cascading Bandits Robust to Adversarial Corruptions
Xie, Jize
Chen, Cheng
Wang, Zhiyong
Li, Shuai
Machine Learning
Online learning to rank sequentially recommends a small list of items to users from a large candidate set and receives the users' click feedback. In many real-world scenarios, users browse the recommended list in order and click the first attractive item without checking the rest. Such behaviors are usually formulated as the cascade model. Many recent works study algorithms for cascading bandits, an online learning to rank framework in the cascade model. However, the performance of existing methods may drop significantly if part of the user feedback is adversarially corrupted (e.g., click fraud). In this work, we study how to resist adversarial corruptions in cascading bandits. We first formulate the ``\textit{Cascading Bandits with Adversarial Corruptions}" (CBAC) problem, which assumes that there is an adaptive adversary that may manipulate the user feedback. Then we propose two robust algorithms for this problem, which assume the corruption level is known and agnostic, respectively. We show that both algorithms can achieve logarithmic regret when the algorithm is not under attack, and the regret increases linearly with the corruption level. The experimental results also verify the robustness of our methods.
title Cascading Bandits Robust to Adversarial Corruptions
topic Machine Learning
url https://arxiv.org/abs/2502.08077