Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon

arXiv:2609.29694 · cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Sample Complexity — 6× in this paper · explained in 15 episodes
• Additivity — 4× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Error Decomposition — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adaptivity — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Contextual Bandits — 1× in this paper · explained in 3 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• List Learning — 1× in this paper · explained in 2 episodes

Sources

• PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
• Fast Rates for Bandit PAC Multiclass Classification
• The Sample Complexity of Multiclass and Sparse Contextual Bandits
• From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
• The Real Price of Bandit Information in Multiclass Classification

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