Accelerated stochastic first-order method for convex optimization under heavy-tailed noise. Chuan He, Zhaosong Lu, 2025. Link
DeMuon: A decentralized Muon for matrix optimization over graphs. Chuan He, Shuyi Ren, Jingwei Mao, Erik G. Larsson, 2025. Link
Low-rank orthogonalization for large-scale matrix optimization with applications to foundation model training. Chuan He, Zhanwang Deng, Zhaosong Lu, 2025. Link
Exact reformulation and optimization for direct metric optimization in binary imbalanced classification. Le Peng, Yash Travadi, Chuan He, Ying Cui, Ju Sun, 2025. Link
Faster stochastic cubic regularized Newton methods with momentum. Yiming Yang, Chuan He, Xiao Wang, Zheng Peng, 2025. Link
Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise. Chuan He, Zhaosong Lu, Defeng Sun, Zhanwang Deng, 2025. Link
Stochastic interior-point methods for smooth conic optimization with applications. Chuan He, Zhanwang Deng, Journal of Machine Learning Research, 2026. Link
Newton-CG methods for nonconvex unconstrained optimization with Hölder continuous Hessian. Chuan He, Heng Huang, Zhaosong Lu, Mathematics of Operations Research, 2025. Link
A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization. Chuan He, Heng Huang, Zhaosong Lu, Computational Optimization and Applications 89 (3), 843-894, 2024. Link
Federated learning with convex global and local constraints. Chuan He, Le Peng, Ju Sun, Transactions on Machine Learning Research, 2024. Link
Decision rule approaches for pessimistic bilevel linear programs under moment ambiguity with facility location applications. Akshit Goyal, Yiling Zhang, Chuan He, INFORMS Journal on Computing 35 (6), 1342-1360, 2023. Link
A Newton-CG based augmented Lagrangian method for finding a second-order stationary point of nonconvex equality constrained optimization with complexity guarantees. Chuan He, Zhaosong Lu, Ting Kei Pong, SIAM Journal on Optimization 33 (3), 1734-1766, 2023. Link
A Newton-CG based barrier method for finding a second-order stationary point of nonconvex conic optimization with complexity guarantees. Chuan He, Zhaosong Lu, SIAM Journal on Optimization 33 (2), 1191-1222, 2023. Link
A parameter-free conditional gradient method for composite minimization under Hölder condition. Masaru Ito, Zhaosong Lu, Chuan He, Journal of Machine Learning Research 24 (166), 1-34, 2023. Link