Tianjiao Ding

PhD Student • Innovation in Data Engineering and Science (IDEAS)University of Pennsylvania Email: tjding@upenn.edu

HeadShotSemiFormal.jpg

Hi there! I am a PhD student at University of Pennsylvania, advised by René Vidal. I work closely with Benjamin D. Haeffele and Yi Ma. Prior to my PhD, I was a research assistant at ShanghaiTech University, advised by Manolis C. Tsakiris and collaborating with Laurent Kneip. I received a master’s degree in applied mathematics and statistics from Johns Hopkins University, and a bachelor’s in computer science with honor from ShanghaiTech.

My research interests center on theoretical foundations of machine learning and emerging applications. On one hand, I use mathematics to understand when and why existing empirical paradigms work. On the other hand, these insights allow me to develop practical algorithms that are more robust, trustworthy, and efficient. As such, my work typically involves theory, controlled simulations, and large-scale applications.

You can view my CV for project highlights, or papers clustered by keywords.

Reaching out to me

I am glad to chat about research, advising, collaborations, life, and fun.

Undergraduate and MS students: If you are interested in doing research with me, feel free to contact me. The recommended time investment is at least 15 hours per week. Students I have mentored have gone on to PhD programs at UC Berkeley, Hong Kong University, MIT, NYU, and to full-time roles at Google and Meta.

Updates

Sep 2024 Two papers accepted to NeurIPS ‘24 (Vancouver)!
Mar 2024 One paper accepted to ICLR ‘24 (Vienna)!
Jan 2024 Excited to give an oral talk of a paper accepted to CPAL ‘24 (Hong Kong)!

Papers

  1. arXiv-colan.png
    Concept Lancet: Representation Decomposition and Transplant for Diffusion-Based Image Editing
    In Under Review, 2025
  2. arXiv-tost.png
    Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
    Ziyang WuTD*, Yifu Lu*Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong YuYi Ma, and Benjamin D. Haeffele
    In Under Review, 2025
  3. NeurIPS24-pace.png
    PaCE: Parsimonious Concept Engineering for Large Language Models
    In Annual Conference on Neural Information Processing Systems, 2024
  4. Neurips24-manifold-clustering.png
    Geometric Analysis of Nonlinear Manifold Clustering
    In Annual Conference on Neural Information Processing Systems, 2024
  5. ICLR24-mlc-clip.png
    Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
    In International Conference on Learning Representations, 2024
  6. CPAL24-hard.gif
    HARD: Hyperplane ARrangement Descent
    TD*Liangzu Peng*, and René Vidal
    In Conference on Parsimony and Learning, 2024
  7. OpenReview23-or2.png
    Outlier-Robust Orthogonal Regression on Manifolds
    TD*Liangzu Peng*, and René Vidal
    In OpenReview, 2023
  8. ICCV23-mcr2-clustering.png
    Unsupervised Manifold Linearizing and Clustering
    In International Conference on Computer Vision, 2023
  9. ICML22-doubly-stochastic-clustering.png
    Understanding Doubly Stochastic Clustering
    In International Conference on Machine Learning, 2022
  10. CVPR22-mcr2-variational.png
    Efficient Maximal Coding Rate Reduction by Variational Forms
    In IEEE Conference on Computer Vision and Pattern Recognition, 2022
  11. arXiv21-boosting.png
    Boosting RANSAC via Dual Principal Component Pursuit
    Yunchen Yang, Xinyue Zhang, TDDaniel P. RobinsonRené Vidal, and Manolis C. Tsakiris
    arXiv preprint arXiv:2110.02918, 2021
  12. CVPR20-dpcp-homo.gif
    Robust Homography Estimation via Dual Principal Component Pursuit
    In IEEE Conference on Computer Vision and Pattern Recognition, 2020
  13. ICML19-dpcp.png
    Noisy Dual Principal Component Pursuit
    In International Conference on Machine Learning, 2019
  14. CVPR18-wireframe.jpg
    Learning to Parse Wireframes in Images of Man-Made Environments
    Kun Huang, Yifan WangZihan ZhouTDShenghua Gao, and Yi Ma
    In IEEE Conference on Computer Vision and Pattern Recognition, 2018