Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
cs.LG, cs.AI, stat.ML
Submitted: 2026-06-12
Updated: 2026-09-24
Terminology
Sources
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- What Doubling Tricks Can and Can't Do for Multi-Armed Bandits
- A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
- Low-rank Bandits with Latent Mixtures
- Gaussian Error Linear Units (GELUs)
- Distilling the Knowledge in a Neural Network
- On the Online Frank-Wolfe Algorithms for Convex and Non-convex Optimizations
- MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
- Online Learning: A Modern Introduction Using Convex Optimization
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Large Language Model Routing with Benchmark Datasets
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- R$^3$AG: Retriever Routing for Retrieval-Augmented Generation
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