X
Xiaoming Yuan
Researcher at University of Hong Kong
Publications - 153
Citations - 8796
Xiaoming Yuan is an academic researcher from University of Hong Kong. The author has contributed to research in topics: Convex optimization & Rate of convergence. The author has an hindex of 41, co-authored 144 publications receiving 7362 citations. Previous affiliations of Xiaoming Yuan include Hong Kong Baptist University & City University of Hong Kong.
Papers
More filters
Journal ArticleDOI
On the $O(1/n)$ Convergence Rate of the Douglas-Rachford Alternating Direction Method
Bingsheng He,Xiaoming Yuan +1 more
TL;DR: This note focuses on the Douglas-Rachford ADM scheme proposed by Glowinski and Marrocco, and aims at providing a simple approach to estimating its convergence rate in terms of the iteration number.
Journal ArticleDOI
The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent
TL;DR: A sufficient condition is presented to ensure the convergence of the direct extension of ADMM, and an example to show its divergence is given, which is not necessarily convergent.
Journal ArticleDOI
Recovering Low-Rank and Sparse Components of Matrices from Incomplete and Noisy Observations
Min Tao,Xiaoming Yuan +1 more
TL;DR: This paper studies the recovery task in the general settings that only a fraction of entries of the matrix can be observed and the observation is corrupted by both impulsive and Gaussian noise, and shows that the resulting model falls into the applicable scope of the classical augmented Lagrangian method.
Journal ArticleDOI
Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization
Junfeng Yang,Xiaoming Yuan +1 more
TL;DR: This paper proposes to linearize the ALM and the ADM for some nuclear norm involved minimization problems such that closed-form solutions of these linearized subproblems can be easily derived.
Journal ArticleDOI
Convergence Analysis of Primal-Dual Algorithms for a Saddle-Point Problem: From Contraction Perspective
Bingsheng He,Xiaoming Yuan +1 more
TL;DR: This paper shows that these new primal-dual methods proposed for solving a saddle-point problem are of the contraction type: the iterative sequences generated by these new methods are contractive with respect to the solution set of the saddle- point problem and the global convergence can be obtained within the analytic framework of contraction-type methods.