Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback

cs.LG, cs.AI, stat.ML

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: To appear in Advances in Neural Information Processing Systems 39 (NeurIPS 2026, Spotlight)

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

Sources

• Robust Mean Estimation under Quantization
• Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes
• One-bit feedback is sufficient for upper confidence bound policies

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks