Publications and Talks

Optimizers for deep learning

Second-Moment Stochastic Approximation Methods [paper]
Tao Jiang, Lin Xiao
arXiv preprint arXiv:2609.36600 (2026)

Stochastic Inertial Krasnoselskii-Mann Iteration Achieves Near-Optimal Sample Complexity [paper]
Tong Yang, Tao Jiang, Yuejie Chi, Ashok Cutkosky, Lin Xiao
arXiv preprint arXiv:2609.28543 (2026)

Stochastic Approximation with Block Coordinate Optimal Stepsizes [paper]
Tao Jiang, Lin Xiao
Submitted to JMLR

Optimization Algorithms and Theory

Range of the displacement operator of PDHG with applications to quadratic and conic programming [paper talk at SIAM OP23]
Tao Jiang, Walaa Moursi, Stephen Vavasis
Revision at Mathematics of Operations Research

A linearly convergent Gauss-Newton subgradient method for ill-conditioned problems [paper]
Damek Davis, Tao Jiang

An inexact l2-norm penalty method for cardinality constrained portfolio optimization [paper]
Tao Jiang, Shuo Wang, Ruochen Zhang, Lang Qin, Jinglian Wu, Delin Wang, Selin Damla Ahipasaoglu
The Engineering Economist (2019)

Machine learning: mathematics for clustering

Re-embedding data to strengthen recovery guarantees of clustering [paper]
Tao Jiang, Samuel Tan, Stephen Vavasis

Recovery of a mixture of Gaussians by sum-of-norms clustering [paper talk at ICCOPT 2019]
Tao Jiang, Stephen Vavasis, Sabrina Chen Wen Zhai
Journal of Machine Learning Research (2020)

Certifying clusters from sum-of-norms clustering [paper talk at ICCOPT 2022]
Tao Jiang, Stephen Vavasis