Tianyang Hu

Researcher at Huawei Noah's Ark Lab.

pic.jpg

I am a researcher at the AI Theory Group of Huawei Noah’s Ark Lab. I obtained my Ph.D. in Statistics from Purdue University, under the supervision of Prof. Guang Cheng. Before that, I received my M.S. in Statistics from the University of Chicago and B.S. in Math from Tsinghua University.

My research aims to advance the theoretical understanding of deep learning and develop theory-inspired new algorithms. I am particularly interested in:

  • Statistical Learning
  • Representation Learning
  • Deep Generative Modeling
  • Understanding Large Language Models

Hiring: I am looking for research interns with a strong machine learning/deep learning background. If you are interested in deep generative models or understanding large language models, please drop me an email.

news

Nov 25, 2023 I will be hosting a session on AI4Math and Understanding LLMs in the 2023 X-AGI conference.
Sep 22, 2023 Two papers on generative modeling are accepted to NeurIPS 2023, including one Spotlight 🔦
Aug 25, 2023 Invited talk @ Conference on ML & Stat, East China Normal University
Jul 7, 2023 Invited talk @ Center for Statistical Science, Tsinghua University
Jun 1, 2023 I just started building my website!

selected publications

  1. NeurIPSSpotlight
    Complexity Matters: Rethinking the Latent Space for Generative Modeling
    Tianyang Hu, Fei Chen, Haonan Wang, and 4 more authors
    Advances in Neural Information Processing Systems, 2023
  2. NeurIPS
    Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
    Weijian Luo, Tianyang Hu, Shifeng Zhang, and 3 more authors
    Advances in Neural Information Processing Systems, 2023
  3. JMLR
    Random Smoothing Regularization in Kernel Gradient Descent Learning
    (**)Liang Ding, Tianyang Hu, Jiahang Jiang, and 3 more authors
    Journal of Machine Learning Research, Accept after minor revision, 2024
  4. UAI
    Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification
    Pawel Piwek, Adam Klukowski, and Tianyang Hu
    In Conference on Uncertainty in Artificial Intelligence, 2023
  5. ICLR
    Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
    Tianyang Hu, Zhili Liu, Fengwei Zhou, and 2 more authors
    International Conference on Learning Representations, 2023
  6. NeurIPSSpotlight
    Understanding Square Loss in Training Overparametrized Neural Network Classifiers
    Tianyang Hu*, Jun Wang*, Wenjia Wang*, and 1 more author
    Advances in Neural Information Processing Systems, 2022
  7. AISTATS
    Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
    Tianyang Hu*, Wenjia Wang*, Cong Lin, and 1 more author
    In International Conference on Artificial Intelligence and Statistics, 2021
  8. JMLR
    Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary
    Tianyang Hu, Ruiqi Liu, Zuofeng Shang, and 1 more author
    Journal of Machine Learning Research, Accept after minor revision, 2024