Image de couverture de livre

Data-dependent Bounds with $T$-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nguyen, Quan, Ito, Shinji, Komiyama, Junpei, Mehta, Nishant A.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Replicability is Asymptotically Free in Multi-armed Bandits
par: Komiyama, Junpei, et autres
Publié: (2024)

Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification
par: Komiyama, Junpei
Publié: (2022)

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
par: Kato, Masahiro, et autres
Publié: (2024)

Near-optimal Per-Action Regret Bounds for Sleeping Bandits
par: Nguyen, Quan, et autres
Publié: (2024)

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
par: Lee, Jongyeong, et autres
Publié: (2024)

High-dimensional Contextual Bandit Problem without Sparsity
par: Komiyama, Junpei, et autres
Publié: (2023)

No-regret incentive-compatible online learning under exact truthfulness with non-myopic experts
par: Komiyama, Junpei, et autres
Publié: (2025)

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
par: Ito, Shinji, et autres
Publié: (2024)

High-dimensional Nonparametric Contextual Bandit Problem
par: Iwazaki, Shogo, et autres
Publié: (2025)

Rate-optimal Design for Anytime Best Arm Identification
par: Komiyama, Junpei, et autres
Publié: (2025)

Fixed Confidence Best Arm Identification in the Bayesian Setting
par: Jang, Kyoungseok, et autres
Publié: (2024)

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
par: Tsuchiya, Taira, et autres
Publié: (2024)

Best-of-$\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling
par: Komiyama, Junpei, et autres
Publié: (2025)

Finite-Time Regret Analysis of Retry-Aware Bandits
par: Tong, Bingkui, et autres
Publié: (2026)

A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for $m$-Set Semi-Bandit Problem
par: Chen, Botao, et autres
Publié: (2026)

Multi-Armed Bandits With Best-Action Queries
par: Bacchiocchi, Francesco, et autres
Publié: (2026)

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
par: Kuroki, Yuko, et autres
Publié: (2023)

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
par: Chase, Zachary, et autres
Publié: (2025)

Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee
par: Hung, Yu-Heng, et autres
Publié: (2025)

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback
par: Stradi, Francesco Emanuele, et autres
Publié: (2024)

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
par: Schlisselberg, Ofir, et autres
Publié: (2025)

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
par: Zhao, Canzhe, et autres
Publié: (2025)

Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention
par: Yang, Junwen, et autres
Publié: (2024)

Optimal Streaming Algorithms for Multi-Armed Bandits
par: Jin, Tianyuan, et autres
Publié: (2024)

Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem
par: Blum, Avrim, et autres
Publié: (2025)

Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
par: Kim, Chaiwon, et autres
Publié: (2025)

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
par: Li, Mengmeng, et autres
Publié: (2025)

Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference
par: Jamshidi, Fateme, et autres
Publié: (2025)

Optimal Data Driven Resource Allocation under Multi-Armed Bandit Observations
par: Burnetas, Apostolos N., et autres
Publié: (2018)

Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem
par: Blum, Avrim, et autres
Publié: (2024)

Achieving PAC Guarantees in Mechanism Design through Multi-Armed Bandits
par: Osogami, Takayuki, et autres
Publié: (2024)

Multi-Armed Bandits with Interference
par: Jia, Su, et autres
Publié: (2024)

Imprecise Multi-Armed Bandits
par: Kosoy, Vanessa
Publié: (2024)

Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
par: Bhuyan, Neelkamal, et autres
Publié: (2023)

Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
par: Zhan, Jingxin, et autres
Publié: (2025)

Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
par: Akash, S, et autres
Publié: (2026)

Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards
par: Mussi, Marco, et autres
Publié: (2024)

Flickering Multi-Armed Bandits
par: Chakraborty, Sourav, et autres
Publié: (2026)

Influential Bandits: Pulling an Arm May Change the Environment
par: Sato, Ryoma, et autres
Publié: (2025)

Bandit Max-Min Fair Allocation
par: Harada, Tsubasa, et autres
Publié: (2025)