Learning While Scheduling Jobs under Context-Dependent Service Rates: An Anytime Rate-Optimal Algorithm
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
- Queue Length Regret Bounds for Contextual Queueing Bandits
- Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
- On Learning the $c\mu$ Rule in Single and Parallel Server Networks
- Design and Scheduling of an AI-based Queueing System
- A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
- Learning to Defer in Congested Systems: The AI-Human Interplay
- Batched Kernelized Bandits: Refinements and Extensions
- Scheduling with Predictions and the Price of Misprediction
- Uniform Bounds for Scheduling with Job Size Estimates
- Bandit-Based Rate Adaptation for a Single-Server Queue
- Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
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