arxiv.org · Jun 2, 2026 04:00 UTC

[2606.01799] Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits

Abstract page for arXiv paper 2606.01799: Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling ...

science tech

Read story

Share on X Share on Facebook

arxiv.org · Jun 2, 2026 04:00 UTC

[2606.00984] Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates

Abstract page for arXiv paper 2606.00984: Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates

science tech

Read story

Share on X Share on Facebook

arxiv.org · Jun 1, 2026 04:00 UTC

[2605.31034] Annealed Softmax Greedy in Many-Armed Bayesian Bandits

Abstract page for arXiv paper 2605.31034: Annealed Softmax Greedy in Many-Armed Bayesian Bandits

science tech

Read story

Share on X Share on Facebook

arxiv.org · May 29, 2026 04:00 UTC

[2605.29748] Instance-dependent Stochastic Lipschitz bandit

Abstract page for arXiv paper 2605.29748: Instance-dependent Stochastic Lipschitz bandit

science

Read story

Share on X Share on Facebook