Imagen de Portada

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Canzhe, Ito, Shinji, Li, Shuai
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Decentralized Asynchronous Multi-player Bandits
por: Fan, Jingqi, et al.
Publicado: (2025)

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
por: Kato, Masahiro, et al.
Publicado: (2024)

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
por: Masoudian, Saeed, et al.
Publicado: (2023)

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
por: Lee, Jongyeong, et al.
Publicado: (2024)

Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
por: Ye, Chenlu, et al.
Publicado: (2025)

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
por: Tsuchiya, Taira, et al.
Publicado: (2023)

A Perturbation Approach to Unconstrained Linear Bandits
por: Jacobsen, Andrew, et al.
Publicado: (2026)

Cascading Bandits Robust to Adversarial Corruptions
por: Xie, Jize, et al.
Publicado: (2025)

Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
por: Tani, Naoto, et al.
Publicado: (2026)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
por: Ito, Shinji, et al.
Publicado: (2025)

Data-dependent Bounds with $T$-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching
por: Nguyen, Quan, et al.
Publicado: (2025)

Low-rank Matrix Bandits with Heavy-tailed Rewards
por: Kang, Yue, et al.
Publicado: (2024)

Influential Bandits: Pulling an Arm May Change the Environment
por: Sato, Ryoma, et al.
Publicado: (2025)

Bandit Max-Min Fair Allocation
por: Harada, Tsubasa, et al.
Publicado: (2025)

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
por: Tsuchiya, Taira, et al.
Publicado: (2024)

Best of both worlds: Stochastic & adversarial best-arm identification
por: Abbasi-Yadkori, Yasin, et al.
Publicado: (2026)

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Θ(T^{2/3})$ and its Application to Best-of-Both-Worlds
por: Tsuchiya, Taira, et al.
Publicado: (2024)

Multi-agent Multi-armed Bandit with Fully Heavy-tailed Dynamics
por: Wang, Xingyu, et al.
Publicado: (2025)

Replicability is Asymptotically Free in Multi-armed Bandits
por: Komiyama, Junpei, et al.
Publicado: (2024)

Combinatorial Allocation Bandits with Nonlinear Arm Utility
por: Shibukawa, Yuki, et al.
Publicado: (2026)

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
por: Chase, Zachary, et al.
Publicado: (2025)

A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
por: Xiong, Zhihan, et al.
Publicado: (2023)

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
por: Ito, Shinji, et al.
Publicado: (2024)

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
por: Kuroki, Yuko, et al.
Publicado: (2023)

New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem
por: Ichikawa, Koji, et al.
Publicado: (2023)

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
por: Wang, Jing, et al.
Publicado: (2025)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
por: Tsuchiya, Taira, et al.
Publicado: (2025)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
por: Li, Long-Fei, et al.
Publicado: (2024)

Outlier-Robust Linear System Identification Under Heavy-tailed Noise
por: Kanakeri, Vinay, et al.
Publicado: (2024)

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
por: Lee, Jongyeong, et al.
Publicado: (2025)

On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits
por: Maynard-Zhang, Leo, et al.
Publicado: (2026)

On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits
por: Maiti, Arnab, et al.
Publicado: (2026)

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
por: Jin, Tianyuan, et al.
Publicado: (2024)

Stochastic Bandits Robust to Adversarial Attacks
por: Wang, Xuchuang, et al.
Publicado: (2024)

Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
por: Oh, Youngmin
Publicado: (2026)

A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
por: Hu, Zicheng, et al.
Publicado: (2025)

Robust Causal Bandits for Linear Models
por: Yan, Zirui, et al.
Publicado: (2023)

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
por: van Erven, Tim, et al.
Publicado: (2025)

Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses
por: Cheng, Zhuoyu, et al.
Publicado: (2026)

Differentially Private Sparse Linear Regression with Heavy-tailed Responses
por: Tian, Xizhi, et al.
Publicado: (2025)