IEEE Transactions on Automatic Control, 2026
We provide a full analysis on the convergence behavior of gradient tracking algorithm (SONATA) for nonconvex nonsmooth problems with composite structure under KL property.
arXiv (under review), 2026
In this paper, we provide a full analysis on our proposed parameter-free algorithm DATOS for composite convex optimization. The manuscript is submitted for publication.
Journal of Machine Learning Research, 2026
In this paper, we propose a unified framework to accelerate decentralized optimization algorithms.
arXiv (under review), 2025
In this paper, we provide a solution for local min-consensus issue appeared in previous adaptive decentralized algorithms by introducing a dual stepsize policy.
To appear at the 60th Asilomar Conference on Signals, Systems, and Computers (Asilomar 2026), 2026
We proposed an adaptive decentralized algorithm for convex optimization without extra line-search steps.
The 64th IEEE Conference on Decision and Control (CDC 2025), 2025
In this paper, we propose the first parameter-free decentralized algorithm for composite convex optimization problems with preliminary analysis.