10 citations · 32 across the 25 of their papers we have counts for
26 papers
Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weak Communication
Chenyu Lu, Zijun Chen, Nian Si
We study distributionally robust reinforcement learning (DR-RL) in the average-reward setting under weak communication. Our main result provides finite-sample guarantees for estima…
Diffusion-Based Policies for Dynamic Control of Stochastic Processing Networks
Baris Ata, Jin Guang, J. Michael Harrison +1
We consider a processing network model with job classes or buffers, exogenous input flows into some classes, processing activities, and servers. Each activity is either…
Causal Estimation of Share-Induced Engagement with Flywheel Effects
Weitao Cheng, Yilin Li, Yong Wang +1
Sustainable user growth in online platforms depends not only on acquiring new users but also on reactivating and engaging existing ones through social sharing features. A well-desi…
Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little's Law
Nanshan Jia, Ramesh Johari, Nian Si +1
In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically condu…
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
Chengyi Nie, Nian Si, Zijie Zhou
The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained b…
FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains
Jiashuo Liu, Siyuan Chen, Zaiyuan Wang +38
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, Futu…
Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
Zitao Wang, Nian Si, Molei Liu
Distributionally robust optimization (DRO) protects statistical learning against distributional shifts by optimizing the worst-case performance over a set of perturbed distribution…
Experimental Designs for Multi-Item Multi-Period Inventory Control
Xinqi Chen, Xingyu Bai, Zeyu Zheng +1
Randomized experiments, or A/B testing, are the gold standard for evaluating interventions, yet they remain underutilized in inventory management. This study addresses this gap by…
ScoreFusion: Fusing Score-based Generative Models via Kullback-Leibler Barycenters
Hao Liu, Junze Tony Ye, Jose Blanchet +1
We introduce ScoreFusion, a theoretically grounded method for fusing multiple pre-trained diffusion models that are assumed to generate from auxiliary populations. ScoreFusion is p…
Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces
Shengbo Wang, Jason Meng, Nian Si +2
We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply cha…
Seller-Side Experiments under Interference Induced by Feedback Loops in Two-Sided Platforms
Zhihua Zhu, Zheng Cai, Liang Zheng +1
Two-sided platforms are central to modern commerce and content sharing and often utilize A/B testing for developing new features. While user-side experiments are common, seller-sid…
Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
Yewen Fan, Nian Si, Xiangchen Song +1
The adoption of deep learning across various fields has been extensive, yet there is a lack of focus on evaluating the performance of deep learning pipelines. Typically, with the i…
Singular Control of (Reflected) Brownian Motion: A Computational Method Suitable for Queueing Applications
Baris Ata, J. Michael Harrison, Nian Si
Motivated by applications in queueing theory, we consider a class of singular stochastic control problems whose state space is the d-dimensional positive orthant. The original prob…
On the Foundation of Distributionally Robust Reinforcement Learning
Shengbo Wang, Nian Si, Jose Blanchet +1
Motivated by the need for a robust policy in the face of environment shifts between training and deployment, we contribute to the theoretical foundation of distributionally robust…
Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach
Nian Si
In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuou…
Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks
Baris Ata, J. Michael Harrison, Nian Si
Motivated by applications in queueing theory, we consider a stochastic control problem whose state space is the -dimensional positive orthant. The controlled process evolves…
Sample Complexity of Variance-reduced Distributionally Robust Q-learning
Shengbo Wang, Nian Si, Jose Blanchet +1
Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which th…
A Finite Sample Complexity Bound for Distributionally Robust Q-learning
Shengbo Wang, Nian Si, Jose Blanchet +1
We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation…
Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems
Yewen Fan, Nian Si, Kun Zhang
Calibration is defined as the ratio of the average predicted click rate to the true click rate. The optimization of calibration is essential to many online advertising recommendati…
Selecting the Best Optimizing System
Nian Si, Yifu Tang, Zeyu Zheng
We formulate selecting the best optimizing system (SBOS) problems and provide solutions for those problems. In an SBOS problem, a finite number of systems are contenders. Inside ea…
Testing Group Fairness via Optimal Transport Projections
Nian Si, Karthyek Murthy, Jose Blanchet +1
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. The proposed test is a flexible…
Robust Bayesian Classification Using an Optimistic Score Ratio
Viet Anh Nguyen, Nian Si, Jose Blanchet
We build a Bayesian contextual classification model using an optimistic score ratio for robust binary classification when there is limited information on the class-conditional, or…
Distributionally Robust Batch Contextual Bandits
Nian Si, Fan Zhang, Zhengyuan Zhou +1
Policy learning using historical observational data is an important problem that has found widespread applications. Examples include selecting offers, prices, advertisements to sen…
Efficient Steady-state Simulation of High-dimensional Stochastic Networks
Jose Blanchet, Xinyun Chen, Peter Glynn +1
We propose and study an asymptotically optimal Monte Carlo estimator for steady-state expectations of a d-dimensional reflected Brownian motion. Our estimator is asymptotically opt…