Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints

arXiv:2608.16375 · cs.LG, cs.AI · Submitted 2026-08-17 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-08-17

Updated: 2026-09-27

Terminology

• Regret — 28× in this paper · explained in 3 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Thompson Sampling — 6× in this paper
• Reward Function — 5× in this paper · explained in 2 episodes
• Contextual Bandits — 3× in this paper · explained in 3 episodes
• Mixture-of-Experts (MoE) — 3× in this paper · explained in 7 episodes
• Multinomial Subset Routing — 3× in this paper
• Theoretical Guarantees — 3× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Combinatorial Bandits with Knapsacks — 1× in this paper
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mixture-of-Experts (MoE) Models — 1× in this paper · explained in 3 episodes
• Mixture-of-Experts The Mixture-of-Experts — 1× in this paper
• Non-stationarity — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Learning with Submodular Functions: A Convex Optimization Perspective
• On the Sublinear Regret of Continuous K-Max Bandits
• Thompson Sampling for Complex Bandit Problems
• MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
• RouteLLM: Learning to Route LLMs with Preference Data
• Sum-max Submodular Bandits
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• Large Language Model Routing with Benchmark Datasets
• Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs

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