1. About Me
  2. Papers
  3. Teaching Fellow
  4. Other Skills
  5. Selected Awards
  6. Contact Me

About Me

Hi! My name is Tianle Liu (/tʰjɛn1 lɤ4 ljoʊ2/, Tyler, 刘天乐 or 劉天樂). I am a fifth-year Ph.D. candidate in statistics at Harvard University, working with Morgane Austern, Natesh S. Pillai, and Xiao-Li Meng. Previously, I obtained my B.S. degree in pure and applied mathematics at Tsinghua University in 2020. There I worked under supervision of Mingsheng Long and Hanzhong Liu. In 2019 I visited Simons Institute, UC Berkeley and Wharton School, University of Pennsylvania (hosted by Edgar Dobriban).

My research interest lies at the intersection of statistical inference, probability, and machine learning. I aim to leverage theoretical insights to advance machine learning algorithms and statistical methodology. I am currently exploring statistical topics motivated by biomedical studies and operations research, especially genomics, clinical trials, and policy optimization. For probability, I am interested in limit theorems under dependence, random matrix, and Markov chain mixing. For machine learning, I am interested in understanding probabilistic flows and diffusion models, and in exploring statistical problems in language models such as instability, watermarking, and uncertain quantification.

I am on the 2024-2025 academic job market!

Papers

* denotes equal contribution or alphabetical order.

  • T. Liu, Xiao-Li Meng, Natesh S. Pillai.
    A Heavily Right Strategy for Integrating Dependent Studies in Any Dimension. Submitted, 2025+. Link

  • Morgane Austern*, Yuanchuan Guo*, Zheng Tracy Ke*, T. Liu*.
    Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Models. In Preparation, 2025+.

  • T. Liu, Morgane Austern.
    Wasserstein-\(p\) Bounds via Cumulant-Based Edgeworth Expansions for \(\alpha\)-Mixing Random Fields. Submitted, 2025+. Link

  • Kenneth Li, T. Liu, Naomi Bashkansky, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg.
    Measuring and Controlling Instruction (In)Stability in Language Model Dialogs. Conference on Language Modeling (COLM), 2024. Oral (7.3%). Link

  • T. Liu, Promit Ghosal, Krishna Balasubramanian, Natesh S. Pillai.
    Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent. Neural Information Processing Systems (NeurIPS), 2023. Link

  • T. Liu, Morgane Austern.
    Wasserstein-\(p\) Bounds in the Central Limit Theorem Under Local Dependence. Electronic Journal of Probability, 2023. Link

  • Xin Lu, T. Liu, Hanzhong Liu, Peng Ding.
    Design-Based Theory for Cluster Rerandomization. Biometrika, 2023. Link

  • Yuchen Zhang*, T. Liu*, Mingsheng Long, Michael I. Jordan.
    Bridging Theory and Algorithm for Domain Adaptation. International Conference on Machine Learning (ICML), 2019. Long Oral Presentation (4.6%). Link

Teaching Fellow

  • STAT 210: Probability Theory (2021 Fall)
  • STAT 111: Introduction to Statistical Inference (2022 Spring)
  • STAT 185: Introduction to Unsupervised Learning (2022 Fall)
  • STAT 170: Quantitative Analysis of Capital Markets (2023 Spring)

Other Skills

  • Languages: Mandarin Chinese (native), English (fluent).
  • Coding: Python (NumPy, SciPy, Pandas, PyTorch), R, JavaScript, OCaml, Wolfram, C/C++; HTML/CSS, Shell, \(\mathrm{\LaTeX}\).
  • Hobbies: Badminton, Bodybuilding, Chinese Calligraphy, Painting & Sketching, Tennis.

Please check out this fun page if you want to learn more about my hobbies.

Selected Awards

Contact Me

Harvard University
Science Center #704
1 Oxford St Cambridge, MA 02138, USA

tianleliu [at] fas [dot] harvard [dot] edu