Bandits with Probing: Optimal Regret and the Limits of Winner Feedback

arXiv:2609.15248 · cs.LG, cs.DS, stat.ML · Submitted 2026-09-14 · Read on arXiv

cs.LG, cs.DS, stat.ML

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 37 pages, 2 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 77× in this paper · explained in 3 episodes
• Minimax Regret — 7× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• Multi-Armed Bandits With Best-Action Queries

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks