Follow the Perturbed Leader for Linear Bandits: sqrt T Regret over General Action Sets

arXiv:2610.17818 · cs.LG, stat.ML · Submitted 2026-10-13 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-10-13

Updated: 2026-10-16

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

Terminology

• Regret — 1× in this paper · explained in 3 episodes

Sources

• Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs
• Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems
• A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for $m$-Set Semi-Bandit Problem
• Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries
• Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization
• Two Proofs of the Fisher Information Inequality via Data Processing Arguments
• Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning

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