Population Based Bandits: Provably Efficient Online Hyperparameter Optimization

Bridging Spherical Black-Box Optimizers

Bridging Spherical Black-Box Optimizers

Understanding Reinforcement Learning for Model Training, and future directions with GRAPE

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling,

The Endgame – Building an Autonomous Optimization Pipeline for Apache Iceberg

- **[Free Apache Iceberg Course](

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

arXiv:2607.09015v1 Announce Type: new Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward sign

Adaptive LLM Routing Using Contextual Bandits and Shared Embedding Space

Large Language Models (LLMs) have revolutionized natural language processing, but their varying capabilities and costs pose challenges in pr

ACM Transactions on Evolutionary Learning and Optimization (telo) Vol 6, Issue 2