About

Hui Zou is a professor at the University of Minnesota's School of Statistics. Her research focuses on statistical methodology and theory, contributing to the development of advanced statistical techniques and their applications. She is involved in the study of statistical inference, methodology, and theory, with a particular emphasis on statistical methodology and theory.

Research topics

• Computer Science
• Artificial Intelligence
• Data science
• Algorithm
• Mathematical optimization
• Applied mathematics
• Mathematics

Selected publications

• Cooperative scheduling for multi-fleet battery swapping in electrified mines: A simulation-based optimization approach

  eTransportation · 2026-02-04

  article1st author
  PublisherDOI

• HIGH-DIMENSIONAL NEWEY–POWELL TEST VIA APPROXIMATE MESSAGE PASSING

  Econometric Theory · 2026-04-21

  preprintOpen accessSenior author

  We propose a high-dimensional extension of the heteroscedasticity test proposed in Newey and Powell (1987). Our test is based on expectile regression in the proportional asymptotic regime where $n/p \to \delta \in (0,1]$ . The asymptotic analysis of the test statistic uses the approximate message passing algorithm, from which we obtain the limiting distribution of the test and establish its asymptotic power. The numerical performance of the test is validated through an extensive simulation study. As real-data applications, we present the analysis based on “international economic growth” data (Belloni et al., 2013), which is found to be homoscedastic, and “supermarket” data (Lan et al., 2016), which is found to be heteroscedastic.

  PublisherOA PDFDOI

• Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers

  ArXiv.org · 2025-06-20

  preprintOpen access

  The success of vehicle electrification relies on efficient and adaptable charging infrastructure. Fixed-location charging stations often suffer from underutilization or congestion due to fluctuating demand, while mobile chargers offer flexibility by relocating as needed. This paper studies the optimal planning and operation of hybrid charging infrastructures that combine both fixed and mobile chargers within urban road networks. We formulate the Hybrid Charging Station Planning and Operation (HCSPO) problem, jointly optimizing the placement of fixed stations and the scheduling of mobile chargers. A charging demand prediction model based on Model Predictive Control (MPC) supports dynamic decision-making. To solve the HCSPO problem, we propose a deep reinforcement learning approach enhanced with heuristic scheduling. Experiments on real-world urban scenarios show that our method improves infrastructure availability - achieving up to 244.4% increase in coverage - and reduces user inconvenience with up to 79.8% shorter waiting times, compared to existing solutions.

  PublisherOA PDFDOI

• Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers

  2025-09-01 · 2 citations

  article

  efficient and adaptable charging infrastructure. Fixed-location charging stations often suffer from underutilization or congestion due to fluctuating demand, while mobile chargers offer flexibility by relocating as needed. This paper studies the optimal planning and operation of hybrid charging infrastructures that combine both fixed and mobile chargers within urban road networks. We formulate the Hybrid Charging Station Planning and Operation (HCSPO) problem, jointly optimizing the placement of fixed stations and the scheduling of mobile chargers. A charging demand prediction model based on Model Predictive Control (MPC) supports dynamic decision-making. To solve the HCSPO problem, we propose a deep reinforcement learning approach enhanced with heuristic scheduling. Experiments on real-world urban scenarios show that our method improves infrastructure availability—achieving up to 244.4% increase in coverage—and reduces user inconvenience with up to 79.8% shorter waiting times, compared to existing solutions.

  PublisherDOI

• FVTF inhibits hepatocellular carcinoma stem properties via targeting DNMT1/miR-34a-5p/FoxM1 axis

  Chinese Medicine · 2025-03-06 · 1 citations

  articleOpen access

  BACKGROUND: Fructus Viticis Total Flavonoids (FVTF) is a novel candidate preparation that possesses anticancer activity. However, the role and mechanism of FVTF-inhibiting human hepatocellular carcinoma (HCC) cell stem properties is unclear. METHODS: cell percentage, and a xenograft model were utilized to investigate the impact of FVTF on HCC cells stemness. PCR array and qRT-PCR were conducted to identify differentially expressed cancer stem-related genes and miRNAs between FVTF-treated and untreated HCC cells, respectively. Pyrosequencing was conducted to assess the DNA methylation level of the miR-34a-5p promoter. A luciferase reporter assay was performed to verify whether FoxM1 serves as a direct target of miR-34a-5p. Additionally, immunohistochemistry of an HCC tissue microarray was carried out to assess the expression levels of DNMT1, FoxM1, and miR-34a-5p. RESULTS: A total of 26 compounds, including 10 flavones, in FVTF were identified. FVTF significantly reduced the ability of tumorsphere and soft agar colony formation, the levels of CD44 protein and BMI1, OCT4 and SOX2 mRNAs in HCC cells, and in vivo tumor initiation ability of HCC cells. Mechanistically, FVTF inhibited HCC cell stem properties via targeting DNMT1/miR-34a-5p/FoxM1 axis. Clinically, DNMT1 expression was inversely correlated with miR-34a-5p expression, whereas a positive correlation was noted between DNMT1 and FoxM1 expression levels, and high DNMT1 levels, low miR-34a-5p levels, and high FoxM1 levels were associated with cancer recurrence. Furthermore, a combination of DNMT1, miR-34a-5p and FoxM1 served as an independent prognostic indicator influencing both DFS and OS in patients with HCC. CONCLUSIONS: FVTF inhibits HCC cell stem properties by targeting DNMT1/miR-34a-5p/FoxM1 axis, which is associated with HCC recurrence and prognosis, and FVTF is a prospective treatment drug for human HCC.

  PublisherOA PDFDOI

• Collaborative Inference for Sparse High-Dimensional Models with Non-Shared Data

  ArXiv.org · 2025-04-28

  preprintOpen accessSenior author

  In modern data analysis, statistical efficiency improvement is expected via effective collaboration among multiple data holders with non-shared data. In this article, we propose a collaborative score-type test (CST) for testing linear hypotheses, which accommodates potentially high-dimensional nuisance parameters and a diverging number of constraints and target parameters. Through a careful decomposition of the Kiefer-Bahadur representation for the traditional score statistic, we identify and approximate the key components using aggregated local gradient information from each data source. In addition, we employ a two-stage partial penalization strategy to shrink the approximation error and mitigate the bias from the high-dimensional nuisance parameters. Unlike existing methods, the CST procedure involves constrained optimization under non-shared and high-dimensional data settings, which requires novel theoretical developments. We derive the limiting distributions for the CST statistic under the null hypothesis and the local alternatives. Besides, the CST exhibits an oracle property and achieves the global statistical efficiency. Moreover, it relaxes the stringent restrictions on the number of data sources required in the current literature. Extensive numerical studies and a real example demonstrate the effectiveness and validity of our proposed method.

  PublisherOA PDFDOI

• Multi-Pathway Nitrogen Metabolism in Providencia manganoxydans AHY1: amo/hao-Independent Heterotrophic Nitrification-Aerobic Denitrification and Multidrug-Heavy Metal Resistance

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access1st authorCorresponding
  PublisherDOI

• Timenet: Prediction of Aquatic Pathogenic Microorganisms Based on Deep Time-Series Modeling and Data Enhancement Techniques

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• dcsvm: Density Convoluted Support Vector Machines

  2025-01-10

  datasetOpen accessSenior author

  Implements an efficient algorithm for solving sparse-penalized support vector machines with kernel density convolution. This package is designed for high-dimensional classification tasks, supporting lasso (L1) and elastic-net penalties for sparse feature selection and providing options for tuning kernel bandwidth and penalty weights. The 'dcsvm' is applicable to fields such as bioinformatics, image analysis, and text classification, where high-dimensional data commonly arise. Learn more about the methodology and algorithm at Wang, Zhou, Gu, and Zou (2023) &lt;<a href="https://doi.org/10.1109%2FTIT.2022.3222767" target="_top">doi:10.1109/TIT.2022.3222767</a>&gt;.

  PublisherOA PDFDOI

• Predicting 5G throughput with BAMMO, a boosted additive model for data with missing observations

  Journal of the Royal Statistical Society Series C (Applied Statistics) · 2024-10-07

  articleOpen accessSenior authorCorresponding

  Abstract To deliver on the promise of 5G, network providers and application developers need to understand the factors impacting millimetre wave (mmWave) 5G throughput. Missing data, however, pose significant challenges for modelling throughput. Even in controlled settings, signal strength data may be only intermittently observed when a device’s connection is weak, leading to missing predictor values in model training. In addition, users may choose not to share their data once the model is deployed, meaning that key predictors may be missing when we want to predict throughput for their devices. To address these challenges, we introduce boosted additive model for data with missing observation (BAMMO), a novel additive model estimator obtained via a componentwise boosting algorithm that naturally incorporates data with missing values in model fitting. We validate BAMMO’s approach to handling missing data by comparing it with competing methods on real 5G network data with a high proportion of missing values and in simulations, finding that it delivers more accurate predictions and takes less time to compute. To identify key predictors of mmWave 5G throughput, we develop a novel extension of sparsity oriented importance learning for BAMMO, giving us a measure of variable importance based on the entire boosting solution path rather than a single selected model.

  PublisherOA PDFDOI

Recent grants

• Flexible Statistical Modelling for High Dimensional Data

  NSF · $180k · 2019–2023

• Collaborative Research: New Statistical Methods and Theory for High-Dimensional Data

  NSF · $174k · 2015–2018

• Novel Inference Procedures for Non-Standard High-Dimensional Regression Models

  NSF · $150k · 2020–2023

• CAREER: New Statistical Methodology and Theory for Mining High-Dimensional Data

  NSF · $400k · 2009–2015

• Statistical Modeling with High-dimensional Data: Variable Selection and Regularization

  NSF · $118k · 2007–2010

Frequent coauthors

• Lingzhou Xue

  38 shared

• Jianqing Fan

  36 shared

• Ping Zhong

  China Agricultural University

  29 shared

• Runze Li

  20 shared

• Zhencai Shen

  China Agricultural University

  19 shared

• Yingyi Chen

  18 shared

• Cun-Hui Zhang

  16 shared

• Qing Mai

  14 shared

Awards & honors

• Fellow, American Statistical Association, 2019
• Fellow of Institute of Mathematical Statistics, 2015
• Web of Science Highly Cited Researcher, 2014 - 2019
• Cogs Outstanding Faculty Award, 2013
• IMS Tweedie Award 2011