Author

David Simchi-Levi

h-index 6 View on Semantic Scholar

We have 4 of 35 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Multi-Turn LLM Conversations under the Least-Recently-Used Policy: Mean-Field Asymptotics and Hit Ratio Approximation

The major workloads in modern large language model (LLM) serving systems have shifted from single-shot LLM calls to multi-turn conversations, where new responses are generated based on the whole conversation history across all previous turns. The hit ratio, i.e., the average fraction of KV caches accessed directly from...

He-Yuan Yao, Chu-Tong Gao, Yuan Lyu et al. · 0 citations

#artificial intelligence Jun 2026

Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation

This work introduces Bayesian in-context experimenters: transformer policies trained to imitate a Bayesian posterior Neyman teacher, and proves this amortized policy can be learned via empirical risk minimization using supervised pretraining.

Jiachun Li, David Simchi-Levi · arXiv.org · 0 citations

Preprint Aug 2026

Refined Thompson Learning for Adaptive Bandits: Power-Efficient Flexibility Scheduling Across Data Centers

A contextual restless multi-armed bandit (CRMAB) framework in which a grid operator requests load reductions without observing internal job-scheduling decisions is proposed, demonstrating the economic potential of data-center flexibility as a grid service and highlighting the importance of high-quality, open-source AI...

Zi-Xi Chen, Yifu Ding, Rui-Cheng Ao et al. · 0 citations

#machine learning Preprint Feb 2026

AI-Generated Measurements for Identification and Inference with Missing Data: A Weak Shadow Variable Approach

This work develops an assumption-lean partial identification framework that uses such measurements as weak shadow variables, defined as outcome-informative proxies that are conditionally independent of missingness given the true outcome and observed covariates.

Hongyu Chen, David Simchi-Levi, Ruoxuan Xiong · 1 citation