Tuorui Peng

Ph.D. student in Statistics

• NowPh.D. student in Statistics — Northwestern University
• FromShenzhen, Guangdong, China
• RouteSZSHS · 2013 → Tsinghua · 2019 → Northwestern · 2023

Interests

The theory of statistics under heavy tails and shape constraints — robust, minimax-optimal, and distribution-free methods in high dimensions.

• Robust statistics
• Heavy-tailed minimax theory
• High-dimensional statistical inference
• Distribution-free & conformal inference
• Statistical learning theory

• Graduate Researcher

  Jan 2025 — Present

  Northwestern University

  • — Project: Robust inference under shape constraints with heavy-tailed noise.
  • — Formulated a novel framework for robust mean estimation under star-shaped constraints, explicitly addressing non-Gaussian and heavy-tailed noise structures.
  • — Derived optimal minimax error bounds and established theoretical guarantees for estimators under non-convex and non-smooth geometric constraints.
  • — Presented the findings in a comprehensive research paper.
  • arXiv:2604.05063

• Undergraduate Dissertation

  Dec 2022 – May 2023

  Tsinghua University

  • — Project: Distribution-free inference and neural-network modeling for gene expression.
  • — Applied Mixture Density Networks (MDN) to model complex, multi-modal conditional distributions for high-dimensional genetic data.
  • — Extended the Conformal Prediction framework to construct distribution-free conformal bands for conditional distribution functions.
  • — Programmed the entire pipeline in Python, achieving predictive coverage guarantees without relying on strong distributional assumptions.

• Undergraduate Researcher & RA

  Dec 2021 – Jul 2022

  Tsinghua University

  • — Project: Large-scale medical-record dataset.
  • — Developed a scalable data pipeline to crawl, parse, and structure case-report articles from PubMed OA.
  • — Formed a large-scale public dataset of patient summaries and their links (160k patient summaries, 293k similarity annotations).
  • — Fine-tuned large language models (LLMs) to automate text mining and medical entity extraction from unstructured biomedical literature.
  • — Published the open-source dataset on Nature Scientific Data.
  • Nature Scientific Data
  • Project website

1. 01

   Robust mean estimation under star-shaped constraints with heavy-tailed noise

   Peng, T., Prasadan, A., & Neykov, M. · arXiv preprint arXiv:2604.05063 · 2026

2. 02

   A large-scale dataset of patient summaries for retrieval-based clinical decision support systems

   Zhao, Z., Jin, Q., Chen, F., Peng, T., & Yu, S. · Scientific Data, 10(1), 909 · 2023

• Five-star Zijing Volunteer

  五星级紫荆志愿者 · Tsinghua University Volunteer Association

  2023

• Honorable Mention — MCM/ICM

  Mathematical Contest in Modeling (COMAP), track A

  2022

• Ma Yuehan Cup — Shooting

  第64届马约翰杯 · 10 m air rifle 4th & air gun 5th

  2021

• Note

  Statistics Note — A Brief Summary of Statistics Minor Courses

  Long-running course summary note for the statistics minor courses at Tsinghua, compiled in LaTeX with an indexed PDF.

  Read
• Note

  High Dimensional Statistics Note 2024-2025

  Reading notes on high-dimensional statistics, following Wainwright, Vershynin, Rigollet–Hütter and van Handel.

  Read