Nian Si

A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints

Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little’s Law

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

Knowledge-Guided Wasserstein Distributionally Robust Optimization

Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning

Towards Accurate Deep Learning Model Selection: A Calibrated Metric Approach