Jiang Hu

[9/2026] Our paper ‘‘An efficient primal dual semismooth Newton method for semidefinite programming’’ has been accepted by Mathematics of Operations Research. [arxiv]

[7/2026] One paper titled ‘‘Decentralized Weakly Convex Optimization Over the Stiefel Manifold’’ is accepted by IEEE Transactions on Signal Processing. [publication]

[7/2026] One paper titled ‘‘Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning’’ is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence. [publication]

[7/2026] One paper titled ‘‘A Grover-compatible Manifold Optimization Algorithm for Quantum Search’’ is accepted by SIAM Journal on Scientific Computing. [link]

[4/2026] One paper titled ‘‘A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms’’ is accepted by International Conference on Machine Learning (ICML) 2026. [publication]

[4/2026] One paper titled ‘‘Worth Their Weight: Randomized and Regularized Block Kaczmarz Algorithms without Preprocessing’’ is accepted by SIAM Journal on Matrix Analysis and Applications. [link]

[9/2025] One paper titled ‘‘Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing’’ is accepted by NeurIPS 2025. [publication]

[9/2025] One paper titled ‘‘Non-convex composite federated learning with heterogeneous data’’ is accepted by Automatica. [publication]

[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. [publication]

[9/2025] One paper titled ‘‘Oracle complexity of augmented Lagrangian methods for nonsmooth manifold optimization’’ is accepted by Mathematics of Operations Research. [publication]

[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 Transactions on Signal Processing. [link]

[4/2024] Honored to receive the Best Paper Award at ICASSP 2024, 1 out of 2826 accepted papers. [publication] [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]