Haoran Xu
Ph.D. Student in Management Science and Engineering, admitted Autumn 2021
Bio
I am a PhD candidate in Management Science and Engineering at Stanford University. My research studies sequential decision making under uncertainty, with a focus on both theoretical rigor and practical impact. In my theoretical research, I am interested in results that provide managerial insights and practical guidance for a broad class of operational decision-making problems. My current theoretical research focuses on online resource allocation and multistage stochastic programming. A main theme of my research is developing algorithms and providing analyses for problems motivated by real-world applications in these areas. Alongside theoretical research, I think solving real-world operational problems is of equal importance. Designing and implementing control methods to enhance the sustainability of complex systems, such as AI data centers, is another main theme of my research.
All Publications
-
Bridging the Discrete and Continuous Reward Theories for Online Linear Programming: The Key Role Played by the Support Size
SSRN.
2026
Abstract
Existing finite support theory for online linear programming gives regret bounds independent of the number of requests but typically polynomial in the reward support size. On the other hand, continuous support theory establishes that the regret is logarithmic in the number of requests. Given the quite different regret behaviors in these two settings, it is natural to study the intermediate regime, where both the number of requests n and the reward-support size S are large but finite. This regime is also important at a practical level, as it describes settings in which the number of customer types and number of requests are both large. We consider the single resource problem with independent and identically distributed requests from a known distribution. Under appropriate regularity conditions, we prove an O(log(min{n, S^2 }) + 1/π_{min}) regret bound for the Fluid Bayes Selector algorithm, where π_{min} denotes the smallest point mass in the marginal distribution of resource consumption. This bound requires no nondegeneracy assumption on the finite support fluid LP. Under additional conditions, every feasible policy incurs Ω(log(min{n, S^2 })) regret. We construct two sequences of instances to show that the 1/π_{min} term is necessary in the worst case but not for every instance. For the multisecretary problem, exact asymptotics under additional smoothness and polynomial support growth establish \sqrt{n} as the exact support size scale at which continuous support theory correctly predicts the leading order term of regret of the large support regime. These results quantify the transition between finite and continuous support regret behavior, and clarify the impact of support size on regret.
- A Two-Layer Framework for Joint Online Configuration Selection and Admission Control 43rd International Conference on Machine Learning 2026
-
A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming
arXiv.
2026
Abstract
We study nonstationary Online Linear Programming (OLP), where n orders arrive sequentially with reward-resource consumption pairs that form a sequence of independent, but not necessarily identically distributed, random vectors. At the beginning of the planning horizon, the decision-maker is provided with a resource endowment that is sufficient to fulfill a significant portion of the requests. The decision-maker seeks to maximize the expected total reward by making immediate and irrevocable acceptance or rejection decisions for each order, subject to this resource endowment. We focus on the challenging single-sample setting, where only one sample from each of the n distributions is available at the start of the planning horizon. We propose a novel re-solving algorithm that integrates a dynamic programming perspective with the dual-based frameworks traditionally employed in stationary environments. In the large-resource regime, where the resource endowment scales linearly with the number of orders, we prove that our algorithm achieves O((logn)^2) regret across a broad class of nonstationary distribution sequences. Our results demonstrate that polylogarithmic regret is attainable even under significant environmental shifts and minimal data availability, bridging the gap between stationary OLP and more volatile real-world resource allocation problems.
-
Online Linear Programming with Batching
arXiv.
2024
Abstract
We study Online Linear Programming (OLP) with batching. The planning horizon is cut into K batches, and decisions on orders can be delayed to the end of their associated batch. The ability to delay decisions improves operational performance, as measured by regret. We study two questions: (1) What is a lower bound on the regret as a function of K and the length of the planning horizon? (2) Which algorithms can achieve this regret lower bound? This paper analyzes these questions when the distribution of the reward has a continuous support. We provide an Ω(logK) regret lower bound in the single-resource case, and we provide pricing algorithms having an O(logK) regret in the setting with Poisson arrivals and multiple types of resources. All the algorithms update the prices at most K times and only delay orders of the first and the last batches. All the regret bounds are independent of the length of the planning horizon. Finally, we study a more realistic large support setting where the number of distinct order types is finite but scales with the total number of orders. We prove that our Θ(logK) bounds still hold for the batching operation of a multisecretary problem with discretized uniform rewards in this large support setting, provided the support grows fast enough. This suggests that the continuous support setting that is the paper's focus serves as a useful theoretical surrogate for the more realistic large finite support setting.
-
A routing and consolidation decision model for containerized air-land intermodal operations
COMPUTERS & INDUSTRIAL ENGINEERING
2020; 141
View details for DOI 10.1016/j.cie.2020.106299
View details for Web of Science ID 000517654200010