64 citations · 279 across the 30 of their papers we have counts for
30 papers
Sparse Decentralized Federated Learning
Shan Sha, Shenglong Zhou, Lingchen Kong +1
Decentralized Federated Learning (DFL) enables collaborative model training without a central server but faces challenges in efficiency, stability, and trustworthiness due to commu…
Revisiting Norm Regularized Optimization
Shenglong Zhou, Xianchao Xiu, Yingnan Wang +1
Sparse optimization has seen its advances in recent decades. For scenarios where the true sparsity is unknown, regularization turns out to be a promising solution. Two popular non-…
0/1 Constrained Optimization Solving Sample Average Approximation for Chance Constrained Programming
Shenglong Zhou, Lili Pan, Naihua Xiu +1
Sample average approximation (SAA) is a tractable approach for dealing with chance constrained programming, a challenging stochastic optimization problem. The constraint of SAA is…
Nonconvex quasi-variational inequalities: stability analysis and application to numerical optimization
Joydeep Dutta, Lahoussine Lafhim, Alain Zemkoho +1
We consider a parametric quasi-variational inequality (QVI) without any convexity assumption. Using the concept of \emph{optimal value function}, we transform the problem into that…
Exact Penalty Method for Federated Learning
Shenglong Zhou, and Geoffrey Ye Li
Federated learning has burgeoned recently in machine learning, giving rise to a variety of research topics. Popular optimization algorithms are based on the frameworks of the (stoc…
Gradient Projection Newton Pursuit for Sparsity Constrained Optimization
Shenglong Zhou
Hard-thresholding-based algorithms have seen various advantages for sparse optimization in controlling the sparsity and allowing for fast computation. Recent research shows that wh…
0/1 Deep Neural Networks via Block Coordinate Descent
Hui Zhang, Shenglong Zhou, Geoffrey Ye Li +1
The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsi…
Test-time Batch Normalization
Tao Yang, Shenglong Zhou, Yuwang Wang +2
Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift. In this paper, targeting of…
FedGiA: An Efficient Hybrid Algorithm for Federated Learning
Shenglong Zhou, Geoffrey Ye Li
Federated learning has shown its advances recently but is still facing many challenges, such as how algorithms save communication resources and reduce computational costs, and whet…
Federated Learning via Inexact ADMM
Shenglong Zhou, Geoffrey Ye Li
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong…
An Oracle Gradient Regularized Newton Method for Quadratic Measurements Regression
Jun Fan, Jie Sun, Ailing Yan +1
Recovering an unknown signal from quadratic measurements has gained popularity due to its wide range of applications, including phase retrieval, fusion frame phase retrieval, and p…
Accretionary Learning with Deep Neural Networks
Xinyu Wei, Biing-Hwang Fred Juang, Ouya Wang +2
One of the fundamental limitations of Deep Neural Networks (DNN) is its inability to acquire and accumulate new cognitive capabilities. When some new data appears, such as new obje…
Communication-Efficient ADMM-based Federated Learning
Shenglong Zhou, Geoffrey Ye Li
Federated learning has shown its advances over the last few years but is facing many challenges, such as how algorithms save communication resources, how they reduce computational…
Gradient Projection Newton Algorithm for Sparse Collaborative Learning Using Synthetic and Real Datasets of Applications
Jun Sun, Lingchen Kong, Shenglong Zhou
Exploring the relationship among multiple sets of data from one same group enables practitioners to make better decisions in medical science and engineering. In this paper, we prop…
Quadratic Convergence of Smoothing Newton's Method for 0/1 Loss Optimization
Shenglong Zhou, Lili Pan, Naihua Xiu +1
It has been widely recognized that the 0/1 loss function is one of the most natural choices for modelling classification errors, and it has a wide range of applications including s…
Computing One-bit Compressive Sensing via Double-Sparsity Constrained Optimization
Shenglong Zhou, Ziyan Luo, Naihua Xiu +1
One-bit compressive sensing gains its popularity in signal processing and communications due to its low storage costs and low hardware complexity. However, it has been a challengin…
Heaviside Set Constrained Optimization: Optimality and Newton Method
Shenglong Zhou, Lili Pan, Naihua Xiu
Data in the real world frequently involve binary status: truth or falsehood, positiveness or negativeness, similarity or dissimilarity, spam or non-spam, and to name a few, with ap…
Sparse SVM for Sufficient Data Reduction
Shenglong Zhou
Kernel-based methods for support vector machines (SVM) have shown highly advantageous performance in various applications. However, they may incur prohibitive computational costs f…
Newton Hard Thresholding Pursuit for Sparse LCP via A New Merit Function
Shenglong Zhou, Meijuan Shang, Lili Pan +1
Solutions to the linear complementarity problem (LCP) are naturally sparse in many applications such as bimatrix games and portfolio section problems. Despite that it gives rise to…
Theoretical and numerical comparison of the Karush-Kuhn-Tucker and value function reformulations in bilevel optimization
Alain Zemkoho, Shenglong Zhou
The Karush-Kuhn-Tucker and value function (lower-level value function, to be precise) reformulations are the most common single-level transformations of the bilevel optimization pr…
Newton method for -regularized optimization
Shenglong Zhou, Lili Pan, Naihua Xiu
As a tractable approach, regularization is frequently adopted in sparse optimization. This gives rise to the regularized optimization, aiming at minimizing the norm or its…
Semismooth Newton-type method for bilevel optimization: Global convergence and extensive numerical experiments
Andreas Fischer, Alain B. Zemkoho, Shenglong Zhou
We consider the standard optimistic bilevel optimization problem, in particular upper- and lower-level constraints can be coupled. By means of the lower-level value function, the p…
Support Vector Machine Classifier via Soft-Margin Loss
Huajun Wang, Yuanhai Shao, Shenglong Zhou +2
Support vector machine (SVM) has attracted great attentions for the last two decades due to its extensive applications, and thus numerous optimization models have been proposed. To…
An Extended Newton-type Algorithm for -Regularized Sparse Logistic Regression and Its Efficiency for Classifying Large-scale Datasets
Rui Wang, Naihua Xiu, Shenglong Zhou
Sparse logistic regression, as an effective tool of classification, has been developed tremendously in recent two decades, from its origination the -regularized version to…