Deyi Liu(刘德意) Ph.D. student in Statistics and Operations Research Department University of North Carolina at Chapel Hill deyi [at] live.unc.edu Github | Google Scholar | CV

Publications & Preprint [Google Scholar]

Stochastic Accelerated Smoothing Methods for Nonsmooth Convex Optimization.
Deyi Liu, Q Tran-Dinh
Under review of Computational Optimization and Applications.

A New Randomized Primal-Dual Algorithm for Convex Optimization with Optimal Last Iterate Rates.
Q Tran-Dinh, Deyi Liu
Under review of Optimization Methods and Software (minor revision).

New Primal-Dual Algorithms for A Class of Nonsmooth and Nonlinear Convex-Concave Minimax Problems.
Yuzixuan Zhu, Deyi Liu, Quoc Tran-Dinh
SIAM Journal on Optimization, 2022.

Robust and Generalizable Visual Representation Learning via Random Convolutions
Zhenlin Xu, Deyi Liu, Junlin Yang, Marc Niethammer
International Conference on Learning Representations, ICLR 2021.

A Newton Frank-Wolfe Method for Constrained Self-Concordant Minimization
Deyi Liu, Volkan Cevher, Quoc Tran-Dinh
Journal of Global Optimization, 2021.

Hybrid variance-reduced SGD algorithms for nonconvex-concave minimax problems
Quoc Tran-Dinh, Deyi Liu, Lam M. Nguyen
Neural Information and Processing Systems, NeurIPS 2020.

An Inexact Interior-Point Lagrangian Decomposition Algorithm with Inexact Oracles
Deyi Liu, Quoc Tran-Dinh
Journal of Optimization Theory and Applications, 2019.