Scholar
Tianyang Hu
Google Scholar ID: mlA_3r0AAAAJ
Assistant Professor, The Chinese University of Hong Kong, Shenzhen
Citations & Impact
Citations
727
H-index
15
i10-index
21
Publications
20
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Selected Publications: - Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary (JMLR, 2025) - Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers (ICML, 2024) - Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion (ICML, 2024) - Complexity Matters: Rethinking the Latent Space for Generative Modeling (NeurIPS Spotlight, 2023) - Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models (NeurIPS, 2023) - Random Smoothing Regularization in Kernel Gradient Descent Learning (JMLR, 2024) - Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding (ICLR, 2023) - Understanding Square Loss in Training Overparametrized Neural Network Classifiers (NeurIPS Spotlight, 2022) - Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network (AISTATS, 2021)
Research Experience
- Previously a Postdoctoral Fellow at the National University of Singapore, working with Prof. Kenji Kawaguchi; and a Research Scientist in the AI Theory Group of Huawei Noah’s Ark Lab.
Education
- Ph.D. in Statistics from Purdue University, supervised by Prof. Guang Cheng; M.S. in Statistics from the University of Chicago; B.S. in Mathematics from Tsinghua University.
Background
- Research Interests: Intersection of Statistics and AI, particularly in Statistical Machine Learning, Representation Learning, and Deep Generative Modeling. Brief Introduction: Currently an Assistant Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen.
Miscellany
- Personal Interests: Special thanks to Yixuan and Taiyun for the photo taken at SUFE in 2023.
