41 citations · 172 across the 26 of their papers we have counts for
28 papers
Mixed-Noise Plug-and-Play with Infimal Convolution Fidelities and Multiple Priors
Ziqi Qin, Hong Ye Tan, Ander Biguri +2
Plug-and-Play (PnP) algorithms are a class of iterative methods for inverse imaging. Within an optimization algorithm, they combine a flexible fidelity term, encoding the forward o…
Federated Primal Dual Fixed Point Algorithm
Ya-Nan Zhu, Jingwei Liang, Xiaoqun Zhang
Federated learning (FL) is a distributed learning paradigm that allows several clients to learn a global model without sharing their private data. In this paper, we generalize a pr…
Robust Graph Representation Learning for Local Corruption Recovery
Bingxin Zhou, Yuanhong Jiang, Yu Guang Wang +4
The performance of graph representation learning is affected by the quality of graph input. While existing research usually pursues a globally smoothed graph embedding, we believe…
Screening for Sparse Online Learning
Jingwei Liang, Clarice Poon
Sparsity promoting regularizers are widely used to impose low-complexity structure (e.g. l1-norm for sparsity) to the regression coefficients of supervised learning. In the realm o…
An Adaptive Rank Continuation Algorithm for General Weighted Low-rank Recovery
Aritra Dutta, Jingwei Liang, Xin Li
This paper is devoted to proposing a general weighted low-rank recovery model and designing a fast SVD-free computational scheme to solve it. First, our generic weighted low-rank r…
A Stochastic Alternating Direction Method of Multipliers for Non-smooth and Non-convex Optimization
Fengmiao Bian, Jingwei Liang, Xiaoqun Zhang
Alternating direction method of multipliers (ADMM) is a popular first-order method owing to its simplicity and efficiency. However, similar to other proximal splitting methods, the…
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang +3
Plug-and-Play (PnP) is a non-convex optimization framework that combines proximal algorithms, for example, the alternating direction method of multipliers (ADMM), with advanced den…
The Fun is Finite: Douglas-Rachford and Sudoku Puzzle -- Finite Termination and Local Linear Convergence
Robert Tovey, Jingwei Liang
In recent years, the Douglas-Rachford splitting method has been shown to be effective at solving many non-convex optimization problems. In this paper we present a local convergence…
Geometry of First-Order Methods and Adaptive Acceleration
Clarice Poon, Jingwei Liang
First-order operator splitting methods are ubiquitous among many fields through science and engineering, such as inverse problems, signal/image processing, statistics, data science…
SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization
Derek Driggs, Junqi Tang, Jingwei Liang +2
We introduce SPRING, a novel stochastic proximal alternating linearized minimization algorithm for solving a class of non-smooth and non-convex optimization problems. Large-scale i…
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang +3
Plug-and-play (PnP) is a non-convex framework that combines ADMM or other proximal algorithms with advanced denoiser priors. Recently, PnP has achieved great empirical success, esp…
Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration
Clarice Poon, Jingwei Liang
The alternating direction method of multipliers (ADMM) is one of the most widely used first-order optimisation methods in the literature owing to its simplicity, flexibility and ef…
On Biased Stochastic Gradient Estimation
Derek Driggs, Jingwei Liang, Carola-Bibiane Schönlieb
We present a uniform analysis of biased stochastic gradient methods for minimizing convex, strongly convex, and non-convex composite objectives, and identify settings where bias is…
Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit
Aritra Dutta, Filip Hanzely, Jingwei Liang +1
The best pair problem aims to find a pair of points that minimize the distance between two disjoint sets. In this paper, we formulate the classical robust principal component analy…
Improving "Fast Iterative Shrinkage-Thresholding Algorithm": Faster, Smarter and Greedier
Jingwei Liang, Tao Luo, Carola-Bibiane Schönlieb
The "fast iterative shrinkage-thresholding algorithm", a.k.a. FISTA, is one of the most well-known first-order optimisation scheme in the literature, as it achieves the worst-case…
Faster FISTA
Jingwei Liang, Carola-Bibiane Schönlieb
The ``fast iterative shrinkage-thresholding algorithm'', a.k.a. FISTA, is one of the most widely used algorithms in the literature. However, despite its optimal theoretical $O(1/k^…
Partial smoothness and constant rank
Adrian S. Lewis, Jingwei Liang
The idea of partial smoothness in optimization blends certain smooth and nonsmooth properties of feasible regions and objective functions. As a consequence, the standard first-orde…
Local Convergence Properties of SAGA/Prox-SVRG and Acceleration
Clarice Poon, Jingwei Liang, Carola-Bibiane Schönlieb
Over the past ten years, driven by large scale optimisation problems arising from machine learning, the development of stochastic optimisation methods have witnessed a tremendous g…
Convergence rates of Forward--Douglas--Rachford splitting method
Cesare Molinari, Jingwei Liang, Jalal Fadili
Over the past years, operator splitting methods have become ubiquitous for non-smooth optimization owing to their simplicity and efficiency. In this paper, we consider the Forward-…
Local Linear Convergence Analysis of Primal-Dual Splitting Methods
Jingwei Liang, Jalal Fadili, Gabriel Peyré
In this paper, we study the local linear convergence properties of a versatile class of Primal-Dual splitting methods for minimizing composite non-smooth convex optimization proble…
A Multi-step Inertial Forward--Backward Splitting Method for Non-convex Optimization
Jingwei Liang, Jalal Fadili, Gabriel Peyré
In this paper, we propose a multi-step inertial Forward--Backward splitting algorithm for minimizing the sum of two non-necessarily convex functions, one of which is proper lower s…
Local Convergence Properties of Douglas--Rachford and ADMM
Jingwei Liang, Jalal Fadili, Gabriel Peyré
The Douglas--Rachford (DR) and alternating direction method of multipliers (ADMM) are two proximal splitting algorithms designed to minimize the sum of two proper lower semi-contin…
Activity Identification and Local Linear Convergence of Forward--Backward-type methods
Jingwei Liang, Jalal Fadili, Gabriel Peyré
In this paper, we consider a class of Forward--Backward (FB) splitting methods that includes several variants (e.g. inertial schemes, FISTA) for minimizing the sum of two proper co…
Activity Identification and Local Linear Convergence of Douglas--Rachford/ADMM under Partial Smoothness
Jingwei Liang, Jalal Fadili, Gabriel Peyré +1
Convex optimization has become ubiquitous in most quantitative disciplines of science, including variational image processing. Proximal splitting algorithms are becoming popular to…