Preprints and Publications

LLM & Foundational Models

• A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
  Chengyi Nie, Nian Si, Zijie Zhou
  International Conference on Machine Learning (ICML), 2026
  

A/B Tests and Experimental Design

• Causal Estimation of Share-Induced Engagement with Flywheel Effects
  Weitao Cheng, Yilin Li, Yong Wang, Nian Si
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
  

• Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little’s Law
  Nanshan Jia, Ramesh Johari, Nian Si, Zeyu Zheng
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
  

• Debiasing Seller-Side Experiments under Multinomial Logit Models in Two-Sided Platforms
  Chenyu Zhang, Yuhang Wu, Zeyu Zheng, Nian Si
  

• Experimental Designs for Multi-Item Multi-Period Inventory Control
  Xinqi Chen, Xingyu Bai, Zeyu Zheng, Nian Si
  ACM Conference on Economics and Computation (EC), 2026
  

• Experimental Design in Live-Interaction Platforms
  Chenran Weng, Xiao Lei, Nian Si
  

• Seller-Side Experiments under Interference Induced by Feedback Loops in Two-Sided Platforms
  Zhihua Zhu, Zheng Cai, Liang Zheng, Nian Si
  

• Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach
  Nian Si
  

• A/B Tests Under a Safety Budget: A Simulation-Optimization Point of View
  Nian Si, Jose Blanchet, Ramesh Johari, Zeyu Zheng
  preprint
  

• Optimal Bidding and Experimentation for Multi-layer Auctions in Online Advertising
  Nian Si, San Gultekin, Jose Blanchet, Aaron Flores
  

Distributional Robustness and Optimal Transport

• Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
  Shengbo Wang, Nian Si
  

• Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processes
  Mingyuan Xu, Zongqi Xia, Tianxi Cai, Doudou Zhou, Nian Si
  

• Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain
  Shengbo Wang, Nian Si
  

• Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
  Zitao Wang, Nian Si, Molei Liu
  

• Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
  Zhenghao Li, Shengbo Wang, Nian Si
  Artificial Intelligence and Statistics Conference (AISTATS), 2026
  Spotlight presentation; top 3% of submissions

• Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
  Zijun Chen, Shengbo Wang, Nian Si
  Neural Information Processing Systems (NeurIPS), 2025
  

• Knowledge-Guided Wasserstein Distributionally Robust Optimization
  Zitao Wang, Ziyuan Wang, Molei Liu, Nian Si
  International Conference on Machine Learning (ICML), 2025
  

• Tractable Robust Markov Decision Processes
  Julien Grand-Clément, Nian Si, Shengbo Wang
  

• Multi-source Stable Variable Importance Measure via Adversarial Machine Learning
  Zitao Wang, Nian Si, Zijian Guo, Molei Liu
  

• Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Artificial Intelligence and Statistics Conference (AISTATS), 2025
  Oral presentation; top 2% of submissions

• On the Foundation of Distributionally Robust Reinforcement Learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  

• Sample Complexity of Variance-reduced Distributionally Robust Q-learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Journal of Machine Learning Research, 2024
  

• A Finite Sample Complexity Bound for Distributionally Robust Q-learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Artificial Intelligence and Statistics Conference (AISTATS), 2023
  

• Distributional Robust Batch Contextual Bandits
  Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet
  Management Science, 2023
  2021 MSOM Student Paper Prize Finalist

• Confidence Regions in Wasserstein Distributionally Robust Estimation
  Jose Blanchet, Karthyek Murthy, Nian Si*
  Biometrika, 2022
  

• Optimal Uncertainty Size in Distributionally Robust Inverse Covariance Estimation
  Jose Blanchet, Nian Si*
  Operations Research Letters, 2019
  

• Robust Strategic Transfer Learning in an Uncertain Environment: from Second- to First-price Auctions
  Nian Si, San Gultekin, Jose Blanchet, Aaron Flores
  

• Testing Group Fairness via Optimal Transport Projections
  Nian Si, Karthyek Murthy, Jose Blanchet, Viet Anh Nguyen
  International Conference on Machine Learning (ICML), 2021
  

• Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
  Nian Si, Jose Blanchet, Soumyadip Ghosh, Mark Squillante
  Neural Information Processing Systems (NeurIPS), 2020
  Spotlight presentation; top 4% of submissions

• Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits
  Nian Si†, Fan Zhang†, Zhengyuan Zhou, Jose Blanchet
  International Conference on Machine Learning (ICML), 2020
  

• Robust Bayesian Classification Using an Optimistic Score Ratio
  Viet Anh Nguyen, Nian Si, Jose Blanchet
  International Conference on Machine Learning (ICML), 2020
  

Theoretical and Computational Reinforcement Learning

• Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values
  Shengbo Wang, Nian Si
  

• Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processes
  Mingyuan Xu, Zongqi Xia, Tianxi Cai, Doudou Zhou, Nian Si
  

• Achieving ε⁻² Dependence for Average-Reward Q-Learning with a New Contraction Principle
  Zijun Chen, Zaiwei Chen, Nian Si, Shengbo Wang
  

• Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain
  Shengbo Wang, Nian Si
  

• Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
  Zhenghao Li, Shengbo Wang, Nian Si
  Artificial Intelligence and Statistics Conference (AISTATS), 2026
  Spotlight presentation; top 3% of submissions

• Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
  Zijun Chen, Shengbo Wang, Nian Si
  Neural Information Processing Systems (NeurIPS), 2025
  

• Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Artificial Intelligence and Statistics Conference (AISTATS), 2025
  Oral presentation; top 2% of submissions

• On the Foundation of Distributionally Robust Reinforcement Learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  

• Sample Complexity of Variance-reduced Distributionally Robust Q-learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Journal of Machine Learning Research, 2024
  

• A Finite Sample Complexity Bound for Distributionally Robust Q-learning
  Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
  Artificial Intelligence and Statistics Conference (AISTATS), 2023
  

• Singular Control of (Reflected) Brownian Motion: A Computational Method Suitable for Queueing Applications
  Baris Ata, Michael Harrison, Nian Si*
  Queueing Systems: Theory and Applications (QUESTA), 2024+
  

• Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks
  Baris Ata, Michael Harrison, Nian Si*
  Stochastic Systems, 2024
  

Simulation

• Efficient Steady-state Simulation of High-dimensional Stochastic Networks
  Jose Blanchet, Xinyun Chen, Peter Glynn, Nian Si*
  Stochastic Systems, 2021
  

• Selecting the Best Optimizing System
  Nian Si, Yifu Tang, Zeyu Zheng
  

• A Preliminary Study of Regularization Framework for Constructing Task-Specific Simulators
  Dilara Aykanat,Zeyu Zheng, Nian Si
  Winter Simulation Conference (WSC), 2023
  

Machine Learning and Platform Operations

• Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems
  Yewen Fan†, Nian Si†, Kun Zhang
  International Conference on Learning Representations (ICLR), 2023
  

• Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
  Yewen Fan, Nian Si, Xiangchen Song, Kun Zhang
  

• ScoreFusion: Fusing Score-based Generative Models via Kullback-Leibler Barycenters
  Hao Liu, Junze (Tony) Ye, Jose Blanchet, Nian Si
  Artificial Intelligence and Statistics Conference (AISTATS), 2025
  Oral presentation; top 2% of submissions

  
  * stands for alphabetical order.
  † stands for equal contribution.

  Last update: 2025-05-20.