Tianyang Hu
Researcher at Huawei Noah's Ark Lab.
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
- NeurIPS
Spotlight Complexity Matters: Rethinking the Latent Space for Generative ModelingAdvances in Neural Information Processing Systems, 2023 - NeurIPSDiff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion ModelsAdvances in Neural Information Processing Systems, 2023
- JMLRRandom Smoothing Regularization in Kernel Gradient Descent LearningJournal of Machine Learning Research, Accept after minor revision, 2024
- UAIExact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for ClassificationIn Conference on Uncertainty in Artificial Intelligence, 2023
- ICLRYour Contrastive Learning Is Secretly Doing Stochastic Neighbor EmbeddingInternational Conference on Learning Representations, 2023
- NeurIPS
Spotlight Understanding Square Loss in Training Overparametrized Neural Network ClassifiersAdvances in Neural Information Processing Systems, 2022 - AISTATSRegularization Matters: A Nonparametric Perspective on Overparametrized Neural NetworkIn International Conference on Artificial Intelligence and Statistics, 2021
- JMLRMinimax Optimal Deep Neural Network Classifiers Under Smooth Decision BoundaryJournal of Machine Learning Research, Accept after minor revision, 2024