Hien Dang

Hawaii_profile_pic_2.png

Welcome, and thank you for visiting! My name is Hien, I am a third-year PhD student at Department of Statistics and Data Science, University of Texas at Austin, where I am fortunate to be advised by Prof. Alessandro Rinaldo and Prof. Pratik Patil.

Previously, I worked as an AI resident at FPT Software AI Center, where I was mentored by Prof. Nhat Ho, Prof. Tan Nguyen and Dr. Hung The Tran. I received my bachelor’s degree in mathematics from the University of Science, Vietnam National University.

My research interests lie broadly in statistical machine learning, high-dimensional statistics, and theory of deep learning. Specifically, I am interested in and have worked on:

  • Statistical foundation for distillation and learning with synthetic data using tools from high-dimensional statistics, such as exact asymptotics and random matrix theory.
  • Learning under data contamination and distribution shifts.
  • The structure of neural network representations, particularly phenomena such as neural collapse and posterior collapse.

Here is my Google Scholar and CV.

My email address: hiendang@utexas.edu

Please feel free to reach out for discussions!

Recent news

Sep 2026 Our paper “Prediction-Only Distillation in Linear and Logistic Regression” has been accepted as a poster at NeurIPS 2026. See you in Atlanta!
Apr 2026 Our paper “Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning” has been accepted as a poster at ICML 2026.

Publications/Preprints

“*” denotes equal contribution.

  1. NeurIPS
    Prediction-Only Distillation in Linear and Logistic Regression
    Hien Dang, Pratik Patil, and Alessandro Rinaldo
    Conference on Neural Information Processing Systems (NeurIPS), 2026
  2. Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
    Hien Dang, Pratik Patil, and Alessandro Rinaldo
    International Conference on Machine Learning (ICML), 2026
  3. On the Mechanisms of Collaborative Learning in VAE Recommenders
    Long Tung Vuong, Julien Monteil, Hien Dang, Volodymyr Vaskovych, Trung Le, and Vu Nguyen
    International Conference on Learning Representations (ICLR), 2026
  4. Preprint
    Why Domain Generalization Fails? A View of Necessity and Sufficiency
    Long Tung Vuong, Vy Vo, Hien Dang, Van-Anh Nguyen, Thanh-Toan Do, Mehrtash Harandi, Trung Le, and Dinh Phung
    arXiv preprint, 2025
  5. Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model
    Hien Dang, Tho Tran, Tan Nguyen, and Nhat Ho
    International Conference on Machine Learning (ICML), 2024
  6. Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
    Hien Dang, Tho Tran, Tan Nguyen, and Nhat Ho
    International Conference on Learning Representations (ICLR), 2024
  7. Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
    Hien Dang*, Tho Tran*, Stanley Osher, Hung Tran-The, Nhat Ho, and Tan Nguyen
    International Conference on Machine Learning (ICML), 2023