Imagen de Portada

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Jing, Zhang, Yu-Jie, Zhao, Peng, Zhou, Zhi-Hua
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

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
por: Zhang, Yu-Jie, et al.
Publicado: (2025)

Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned Distributions
por: Wang, Jing, et al.
Publicado: (2026)

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs
por: Wang, Jing, et al.
Publicado: (2026)

Provably Efficient Online RLHF with One-Pass Reward Modeling
por: Li, Long-Fei, 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)

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
por: Tajdini, Artin, 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)

From One-Pass SGD to Data Reuse: Mini-Batch Scaling Laws in Sketched Linear Regression
por: Chen, Ziyan, et al.
Publicado: (2026)

Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions
por: Kang, Yue, et al.
Publicado: (2025)

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
por: Shi, Jiang-Xin, et al.
Publicado: (2023)

Sparse Linear Regression when Noises and Covariates are Heavy-Tailed and Contaminated by Outliers
por: Sasai, Takeyuki, et al.
Publicado: (2024)

$(ε, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits
por: Genalti, Gianmarco, et al.
Publicado: (2023)

Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
por: Yu, Sanghoon, et al.
Publicado: (2026)

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
por: Zhao, Canzhe, et al.
Publicado: (2025)

High-Dimensional Tail Index Regression
por: Sasaki, Yuya, et al.
Publicado: (2024)

Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits
por: Tamás, Ambrus, et al.
Publicado: (2024)

Understanding Robust Machine Learning for Nonparametric Regression with Heavy-Tailed Noise
por: Feng, Yunlong, et al.
Publicado: (2025)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
por: Li, Long-Fei, et al.
Publicado: (2024)

Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization
por: Zhao, Peng, et al.
Publicado: (2021)

Linear and Neural Dueling Bandits with Delayed Feedback
por: Wang, Xiangyi, et al.
Publicado: (2026)

Catoni-Style Change Point Detection for Regret Minimization in Non-Stationary Heavy-Tailed Bandits
por: Genalti, Gianmarco, et al.
Publicado: (2025)

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
por: Flynn, Hamish, et al.
Publicado: (2023)

Beyond Task Diversity: Provable Representation Transfer for Sequential Multi-Task Linear Bandits
por: Duong, Thang, et al.
Publicado: (2025)

Tail Annealing for Heavy-Tailed Flow Matching
por: Pachebat, Jean
Publicado: (2026)

Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
por: Li, Long-Fei, et al.
Publicado: (2024)

A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits
por: Simchi-Levi, David, et al.
Publicado: (2022)

Models of Heavy-Tailed Mechanistic Universality
por: Hodgkinson, Liam, et al.
Publicado: (2025)

Heavy-Tailed Diffusion Models
por: Pandey, Kushagra, et al.
Publicado: (2024)

Asynchronous Heavy-Tailed Optimization
por: Sun, Junfei, et al.
Publicado: (2026)

Contextual Linear Bandits with Delay as Payoff
por: Zhang, Mengxiao, et al.
Publicado: (2025)

Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity
por: Huang, Xinmeng, et al.
Publicado: (2023)

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

Data Deletion for Linear Regression with Noisy SGD
por: Xia, Zhangjie, et al.
Publicado: (2024)

Extended UCB Policies for Multi-armed Bandit Problems
por: Liu, Keqin, et al.
Publicado: (2011)

Exploratory Machine Learning with Unknown Unknowns
por: Zhao, Peng, et al.
Publicado: (2020)

Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
por: Xie, Yan-Feng, et al.
Publicado: (2026)

Federated Linear Dueling Bandits
por: Huang, Xuhan, et al.
Publicado: (2025)

Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits
por: Huang, Ziyi, et al.
Publicado: (2024)

Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity
por: Das, Santanu, et al.
Publicado: (2026)

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
por: He, Di, et al.
Publicado: (2026)