Copertina

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Jongyeong, Honda, Junya, Ito, Shinji, Oh, Min-hwan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
di: Kim, Chaiwon, et al.
Pubblicazione: (2025)

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

A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for $m$-Set Semi-Bandit Problem
di: Chen, Botao, et al.
Pubblicazione: (2026)

Thompson Exploration with Best Challenger Rule in Best Arm Identification
di: Lee, Jongyeong, et al.
Pubblicazione: (2023)

Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems
di: Chen, Botao, et al.
Pubblicazione: (2025)

Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
di: Zhan, Jingxin, et al.
Pubblicazione: (2025)

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

Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
di: Lee, Joongkyu, et al.
Pubblicazione: (2024)

Exploration via Feature Perturbation in Contextual Bandits
di: Yi, Seouh-won, et al.
Pubblicazione: (2025)

Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
di: Lee, Joongkyu, et al.
Pubblicazione: (2026)

Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning
di: Lee, Harin, et al.
Pubblicazione: (2026)

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

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

Optimal and Practical Batched Linear Bandit Algorithm
di: Yu, Sanghoon, et al.
Pubblicazione: (2025)

Lasso Bandit with Compatibility Condition on Optimal Arm
di: Lee, Harin, et al.
Pubblicazione: (2024)

Infrequent Exploration in Linear Bandits
di: Lee, Harin, et al.
Pubblicazione: (2025)

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

Improved Online Confidence Bounds for Multinomial Logistic Bandits
di: Lee, Joongkyu, et al.
Pubblicazione: (2025)

Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
di: Lee, Joongkyu, et al.
Pubblicazione: (2026)

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

Optimal Regret of Bernoulli Bandits under Global Differential Privacy
di: Azize, Achraf, et al.
Pubblicazione: (2025)

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

Learning with Posterior Sampling for Revenue Management under Time-varying Demand
di: Shimizu, Kazuma, et al.
Pubblicazione: (2024)

Blessings of Multiple Good Arms in Multi-Objective Linear Bandits
di: Ann, Heesang, et al.
Pubblicazione: (2026)

Minimax Optimal Reinforcement Learning with Quasi-Optimism
di: Lee, Harin, et al.
Pubblicazione: (2025)

Queueing Matching Bandits with Preference Feedback
di: Kim, Jung-hun, et al.
Pubblicazione: (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
di: Tsuchiya, Taira, et al.
Pubblicazione: (2024)

Stochastic Matching Bandits with Rare Optimization Updates
di: Kim, Jung-hun, et al.
Pubblicazione: (2025)

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

Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
di: Kim, Seok-Jin, et al.
Pubblicazione: (2024)

Thompson Sampling for Multi-Objective Linear Contextual Bandit
di: Park, Somangchan, et al.
Pubblicazione: (2025)

Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
di: Hwang, Taehyun, et al.
Pubblicazione: (2026)

Oracle-Efficient Combinatorial Semi-Bandits
di: Kim, Jung-hun, et al.
Pubblicazione: (2025)

Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
di: Chen, Yu, et al.
Pubblicazione: (2026)

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback
di: Stradi, Francesco Emanuele, et al.
Pubblicazione: (2024)

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
di: Schlisselberg, Ofir, et al.
Pubblicazione: (2025)

Experimental Design for Semiparametric Bandits
di: Kim, Seok-Jin, et al.
Pubblicazione: (2025)

Multi-Player Approaches for Dueling Bandits
di: Raveh, Or, et al.
Pubblicazione: (2024)

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
di: Kang, Hyungkyu, et al.
Pubblicazione: (2025)