Jiang Hu
 |
Assistant professor Shuangqing Complex Blgd. C634 Email: jianghu@tsinghua.edu.cn, hujiangopt@gmail.com |
About me
I am an Assistant Professor at the Yau Mathematical Sciences Center, Tsinghua University. I received my Ph.D. from Peking University and have held research positions at the Chinese University of Hong Kong, Harvard Medical School, and the University of California, Berkeley. My current research focuses on mathematical optimization and its applications in machine learning and artificial intelligence.
News
[9/2025] One paper titled ‘‘Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing’’ is accepted by NeurIPS 2025.
[9/2025] One paper titled ‘‘Non-convex composite federated learning with heterogeneous data’’ is accepted by Automatica. [link]
[9/2025] One paper titled ‘‘Decentralized projected Riemannian gradient method for smooth optimization on compact submanifolds embedded in the Euclidean space’’ is accepted by Numerische Mathematik. [link]
[9/2025] One paper titled ‘‘Oracle complexity of augmented Lagrangian methods for nonsmooth manifold optimization’’ is accepted by Mathematics of Operations Research. [link]
[3/2025] One paper titled ‘‘On the local convergence of the semismooth Newton method for composite optimization’’ is accepted by Journal of Scientific Computing. [link]
[2/2025] One paper titled ‘‘Achieving Local Consensus over Compact Submanifolds’’ is accepted by IEEE Transactions on Automatic Control. [link]
[1/2025] One paper titled ‘‘An Augmented Lagrangian Primal-Dual Semismooth Newton Method for Multi-block Composite Optimization’’ is accepted by Journal of Scientific Computing. [link]
[12/2024] One paper titled ‘‘Decentralized projected Riemannian stochastic recursive momentum method for nonconvex optimization’’ is accepted by AAAI 2025. [link]
[9/2024] One paper titled ‘‘Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data’’ is accepted by NeurIPS 2024. [link]
[7/2024] Our manuscript titled ‘‘Improving the communication in decentralized manifold optimization through single-step consensus and compression’’ is on arxiv. [arxiv]
[5/2024] One paper titled ‘‘Convergence analysis of an adaptively regularized natural gradient method’’ is accepted by IEEE Transaction on Signal Processing. [link]
[4/2024] Honored to receive the Best Paper Award at ICASSP 2024, 1 out of 2826 accepted papers. [link] [page]
[2/2024] One paper titled ‘‘A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity’’ is accepted by Journal of Machine Learning Research. [link]
[1/2024] One paper titled ‘‘Riemannian Natural Gradient Methods’’ is published at SIAM Journal on Scientific Computing. [link]