Research areas

Mathematical Optimization, Machine Learning, Artificial Intelligence

Education

2011-2015 Bachelor, Hunan University

2015-2020 Doctor, Peking University

Research experience

2025/8-present Assistant professor, YAU Mathematical Science Center, Tsinghua University

2024-2025 Postdoctoral, University of California, Berkeley

2022-2024 Postdoctoral, Harvard Medical School

2021-2022 Postdoctoral, The Chinese University of Hong Kong

Awards

2024 Best paper award at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024

Publications

1. K. Deng, J. Hu†, J. Wu, Z. Wen, Oracle complexity of augmented Lagrangian methods for nonsmooth manifold optimization. Accepted at Mathematics of Operations Research (2025+).

2. J. Hu, T. Tian, S. Pan, Z. Wen, On the local convergence of the semismooth Newton method for composite optimization. Journal of Scientific Computing 103, 59 (2025).

3. J. Hu, J. Zhang, K. Deng, Achieving Local Consensus over Compact Submanifolds. IEEE Transactions on Automatic Control (2025).

4. Z. Deng, K. Deng, J. Hu†, Z. Wen, An Augmented Lagrangian Primal-Dual Semismooth Newton Method for Multi-block Composite Optimization. Journal of Scientific Computing, 102, 65 (2025).

4. K. Deng, J. Hu†, Decentralized projected Riemannian stochastic recursive momentum method for smooth optimization on compact submanifolds. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2025).

5. J. Zhang, J. Hu†, A. So, M. Johansson, Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data. Advances in Neural Information Processing Systems 37: Proceedings of the 2024 Conference (NeurIPS 2024).

6. J. Zhang, J. Hu, M. Johansson, Composite federated learning with heterogeneous data. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024. won Best Paper Award! (Approximately 1/3000)

7. J. Wu, J. Hu†, H. Zhang, Z. Wen, Convergence analysis of an adaptively regularized natural gradient method. IEEE Transactions on Signal Processing, 72, pp.2527-2542 (2024).

8. J. Hu, K. Deng, J. Wu, Q. Li, A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity. Journal of Machine Learning Research, 25(56), 1-32 (2024).

9. J. Hu, R. Ao, A. M.-C. So, M. Yang, Z. Wen, Riemannian Natural Gradient Methods. SIAM Journal on Scientific Computing, 46(1), A204-A231 (2024).

10. J. Hu, X. Liu, Z. Wen, Y. Yuan, A Brief Introduction to Manifold Optimization, Journal of the Operations Research Society of China, 8, 199-248 (2020).

11. J. Hu, B. Jiang, L. Lin, Z. Wen, Y. Yuan, Structured Quasi-Newton Methods for Optimization with Orthogonality Constraints, SIAM Journal on Scientific Computing, 41(4), A2239-A2269 (2019).

12. J. Hu, A. Milzarek, Z. Wen, Y. Yuan. Adaptive Quadratically Regularized Newton Method for Riemannian Optimization. SIAM Journal on Matrix Analysis and Applications, 39(3), 1181-1207 (2018).