T. Tony Cai

About

T. Tony Cai is the Daniel H. Silberberg Professor of Statistics and Data Science at the University of Pennsylvania's Wharton School. His research interests encompass statistical machine learning, high-dimensional statistics, large-scale inference, functional data analysis, and statistical decision theory, with applications to genomics and financial econometrics. He has held his position at Wharton since 2000 and was named Dorothy Silberberg Professor in 2007. Professor Cai has received numerous professional awards and honors, including being elected as a Fellow of the American Association for the Advancement of Science in 2023, and serving as President-elect, President, and Past President of the Institute of Mathematical Statistics from 2023 to 2025. He has also been recognized with awards such as the Noether Distinguished Scholar Award from the American Statistical Association in 2023, the Laplace Lecturer of the Bernoulli Society in 2021, and the International Chinese Statistical Association Distinguished Achievement Award in 2019. His academic background includes a PhD from Cornell University obtained in 1996. Throughout his career, he has contributed significantly to the fields of statistics and data science through research, teaching, and leadership roles.

Research topics

• Internal medicine
• Intensive care medicine
• Medicine
• Mathematics
• Statistics
• Dermatology
• Microbiology
• Algorithm
• General surgery
• Mathematical optimization

Selected publications

• Heteroskedastic PCA: Algorithm, optimality, and applications

  The Annals of Statistics · 2022 · 69 citations

  A general framework for principal component analysis (PCA) in the presence of heteroskedastic noise is introduced. We propose an algorithm called HeteroPCA, which involves iteratively imputing the diagonal entries of the sample covariance matrix to remove estimation bias due to heteroskedasticity. This procedure is computationally efficient and provably optimal under the generalized spiked covariance model. A key technical step is a deterministic robust perturbation analysis on singular subspace…

  DOI

• Epidemiology, Risk Factors, and Interventions for Suicide in Chinese Populations: A Systematic Review, Scoping Review, and Meta-analyses

  2025-09-26

  report
  PublisherDOI

• Identification of Risk Factors in Patients with Recurrent Cystitis May Improve Individualized Management

  Preprints.org · 2025-09-26

  preprintOpen access

  Background/Objectives: Management of acute episodes of lower urinary tract infections (LUTI) depends on whether they are sporadic or recurrent. We aimed to define factors that differentiate patients with acute sporadic cystitis (AC) from those with recurrent cystitis (RC) and thereby improve individualized management. Methods: We performed a post-hoc analysis of data from the prospective, multinational GPIU.COM-Study. Female patients with an acute episode of LUTI completed the Acute Cystitis Sym…

  PublisherOA PDFDOI

• Minimax and adaptive transfer learning for nonparametric classification under distributed differential privacy constraints

  Journal of the Royal Statistical Society Series B (Statistical Methodology) · 2025-11-11

  article

  Abstract This paper considers minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. Our study is conducted within a heterogeneous framework, encompassing diverse sample sizes, varying privacy parameters, and data heterogeneity across different servers. We first establish the minimax misclassification rate, precisely characterizing the effects of privacy constraints, source samples, and target sam…

  PublisherDOI

• Consensus position statement on advancing the classification of patients and tests of cure in studies of antibiotic treatment of complicated urinary tract infections.

  RWTH Publications (RWTH Aachen) · 2025-10-01

  articleOpen access

  Complicated urinary tract infections denote an important research field for new antibiotics against Gram-negative pathogens. There is, however, increasing concern that this disease entity is too vaguely defined, leading to heterogeneous study populations and risk of bias. We analysed researchers' adherence to the US Food and Drug Administration (FDA) guidance on complicated urinary tract infection and assessed risk of bias using a three-step procedure: literature review of full-text articles on…

  PublisherOA PDFDOI

Recent grants

• FRG: Collaborative Research: Statistical Inference for High-Dimensional Data: Theory, Methodology and Applications

  NSF · $851k · 2009–2013

• Theory and Methods for Estimation of Nonsmooth Functionals and Detection of Simultaneous Signals

  NSF · $486k · 2014–2017

• FRG: Collaborative Research: Statistical Inference for High-Dimensional Data: Theory, Methodology and Applications

  NSF · $143k · 2009–2013

Frequent coauthors

• Truls E. Bjerklund Johansen

  231 shared

• Riccardo Bartoletti

  University of Pisa

  170 shared

• Paolo Verze

  University of Salerno

  110 shared

• Kurt G. Naber

  Technical University of Munich

  99 shared

• Giovanni Liguori

  University of Campania "Luigi Vanvitelli"

  97 shared

• Alessandro Palmieri

  University of Naples Federico II

  89 shared

• Michele Rizzo

  University of Trieste

  88 shared

• Zhikuan Jia

  Northwest A&F University

  87 shared

Education

• Urologist, Department of Urology

  University of Florence

  2007

• MD, Department of urology

  University of Florence

  2002

Awards & honors

• President-elect, President, and Past President, Institute of…
• Elected as a Fellow of the American Association for the Adva…
• Noether Distinguished Scholar Award, American Statistical As…
• Laplace Lecturer of the Bernoulli Society, 10th World Congre…
• International Chinese Statistical Association Distinguished…

Similar researchers at University of Pennsylvania

• Ron Anafih-26
• Dennis DeTurckh-23
• Ian J. Barnetth-20