activity
20182020
most citedLinear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming

2 citations · 2 across the 5 of their papers we have counts for

collaborators

6 papers

math.OC20202 cited

Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming

Daoli Zhu, Lei Zhao

Linear constrained convex programming has many practical applications, including support vector machine and machine learning portfolio problems. We propose the randomized primal-du…

math.OC2020

Level-set Subdifferential Error Bounds and Linear Convergence of Variable Bregman Proximal Gradient Method

Daoli Zhu, Sien Deng, Minghua Li +1

In this work, we develop a level-set subdifferential error bound condition aiming towards convergence rate analysis of a variable Bregman proximal gradient (VBPG) method for a broa…

math.OC2020

A First-Order Primal-Dual Method for Nonconvex Constrained Optimization Based On the Augmented Lagrangian

Daoli Zhu, Lei Zhao, Shuzhong Zhang

Nonlinearly constrained nonconvex and nonsmooth optimization models play an increasingly important role in machine learning, statistics and data analytics. In this paper, based on…

math.OC2019

Linear Convergence of Variable Bregman Stochastic Coordinate Descent Method for Nonsmooth Nonconvex Optimization by Level-set Variational Analysis

Lei Zhao, Daoli Zhu

Large-scale nonconvex and nonsmooth problems have attracted considerable attention in the fields of compress sensing, big data optimization and machine learning. Exploring effectiv…

math.OC2019

Stochastic Primal-Dual Coordinate Method with Large Step Size for Composite Optimization with Composite Cone-constraints

Daoli Zhu, Lei Zhao

We introduce a stochastic coordinate extension of the first-order primal-dual method studied by Cohen and Zhu (1984) and Zhao and Zhu (2018) to solve Composite Optimization with Co…

math.OC2018

Stochastic Primal-Dual Coordinate Method for Nonlinear Convex Cone Programs

Daoli Zhu, Lei Zhao

Block coordinate descent (BCD) methods and their variants have been widely used in coping with large-scale nonconstrained optimization problems in many fields such as imaging proce…