Nearly Optimal Algorithms for Adversarial Kernelized Bandits

arXiv:2605.10299 · cs.LG · Submitted 2026-05-11 · Read on arXiv

cs.LG

Submitted: 2026-05-11

Updated: 2026-10-17

Comments: 47 pages. Accepted at NeurIPS 2026. This version corrects minor errors and typographical mistakes in v1

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

Terminology

• Regret — 2× in this paper · explained in 4 episodes
• Hilbert Space — 1× in this paper · explained in 2 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Regret Guarantees — 1× in this paper · explained in 2 episodes
• Reproducing Kernel Hilbert Space (RKHS) — 1× in this paper · explained in 7 episodes
• Reward Function — 1× in this paper · explained in 4 episodes

Sources

• Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere
• Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
• Multi-Scale Zero-Order Optimization of Smooth Functions in an RKHS
• On Regret Bounds of Thompson Sampling for Bayesian Optimization
• Near-Optimal Regret in Adversarial Kernel Bandits

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