Suchergebnisse - stochastic variance-reduced algorithm

A variance‐reduced distributed stochastic momentum algorithm over directed networks von Gong, Xiuhui, Gao, Juan, Liu, Xinwei

“… ‐reduced distributed stochastic momentum algorithm over directed networks, named DSM‐SAGA, is developed. DSM‐SAGA is a combination of the heavy …”
Volltext

Single-Loop Variance-Reduced Stochastic Algorithm for Nonconvex-Concave Minimax Optimization von Jiang, Xia, Zhu, Linglingzhi, Zheng, Taoli, So, Anthony Man-Cho

“… In this paper, we develop a novel probabilistic variance reduction updating scheme and propose a single-loop algorithm called the probabilistic variance-reduced smoothed gradient descent-ascent (PVR-SGDA) algorithm …”
Volltext

Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization von Zhang, Junyu, Xiao, Lin

“… We propose a class of stochastic variance-reduced prox-linear algorithms for solving such problems and bound their sample complexities for finding an ϵ …”
Volltext

A stochastic variance-reduced coordinate descent algorithm for learning sparse Bayesian network from discrete high-dimensional data von Shajoonnezhad, Nazanin, Nikanjam, Amin

“… Besides, we implement a block-wised stochastic coordinate descent algorithm to optimize the score function …”
Volltext

Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemannian Manifolds von Zhou, Pan, Yuan, Xiao-Tong, Yan, Shuicheng, Feng, Jiashi

“… ) algorithm to solve the finite-sum and online Riemannian non-convex minimization problems. At the core of R-SPIDER is a recursive semi-stochastic gradient estimator …”
Volltext

A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization von Zhou, Pan, Yuan, Xiao-Tong, Lin, Zhouchen, Hoi, Steven C.H.

“… Despite the success of stochastic variance-reduced gradient (SVRG) algorithms in solving large-scale problems, their stochastic gradient complexity often scales linearly with data size and is expensive for huge data …”
Volltext

Two fast variance-reduced proximal gradient algorithms for SMVIPs-Stochastic Mixed Variational Inequality Problems with suitable applications to stochastic network games and traffic assignment problems von Yang, Zhen-Ping, Lin, Gui-Hua

“… In this paper, we propose two proximal gradient algorithms with variance reduction for stochastic mixed variational inequality problems …”
Volltext

Communication-Efficient Federated Learning: A Variance-Reduced Stochastic Approach With Adaptive Sparsification von Wang, Bin, Fang, Jun, Li, Hongbin, Zeng, Bing

“… Federated learning (FL) is an emerging distributed machine learning paradigm that aims to realize model training without gathering the data from data sources …”
Volltext

Accelerated variance-reduced methods for saddle-point problems von Borodich, Ekaterina, Tominin, Vladislav, Tominin, Yaroslav, Kovalev, Dmitry, Gasnikov, Alexander, Dvurechensky, Pavel

“… for the primal and dual variables. For such problems, under the average-smoothness assumption, we propose accelerated stochastic variance-reduced algorithms with optimal up to logarithmic factors complexity bounds …”
Volltext

Stochastic variance reduced gradient with hyper-gradient for non-convex large-scale learning von Yang, Zhuang

“… With faster convergence rate, there have been tremendous studies on developing stochastic variance reduced algorithms to solve these non-convex optimization problems …”
Volltext

Cocoercivity, smoothness and bias in variance-reduced stochastic gradient methods von Morin, Martin, Giselsson, Pontus

“… With the purpose of examining biased updates in variance-reduced stochastic gradient methods, we introduce SVAG, a SAG/SAGA-like method with adjustable bias …”
Volltext

Loopless Variance Reduced Stochastic ADMM for Equality Constrained Problems in IoT Applications von Liu, Yuanyuan, Geng, Jiacheng, Shang, Fanhua, An, Weixin, Liu, Hongying, Zhu, Qi

“… Recently, several stochastic variance reduced ADMM algorithms (e.g., SVRG-ADMM) have made exciting progress, such as linear convergence for strongly convex (SC) problems …”
Volltext

Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport von Sato, Hiroyuki, Kasai, Hiroyuki, Mishra, Bamdev

“… This paper proposes a novel Riemannian extension of the Euclidean stochastic variance reduced gradient (R-SVRG …”
Volltext

A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates von Zhou, Kaiwen, Shang, Fanhua, Cheng, James

“… , sparse and asynchronous) due to the existence of perturbation. In this paper, we introduce a simple stochastic variance reduced algorithm (MiG …”
Volltext

Stochastic Variance-Reduced Majorization-Minimization Algorithms von Phan, Duy-Nhat, Bartz, Sedi, Guha, Nilabja, Phan, Hung M

“… Consequently, effective algorithms for such scenarios are scarce. We introduce and study three stochastic variance-reduced majorization-minimization (MM …”
Volltext

Variance Reduced Stochastic Proximal Algorithm for AUC Maximization von Soham Dan, Sahoo, Dushyant

“… However, these stochastic algorithms cannot be directly used when non-decomposable pairwise performance measures are used such as Area under the ROC curve (AUC …”
Volltext

SARAH-based Variance-reduced Algorithm for Stochastic Finite-sum Cocoercive Variational Inequalities von Beznosikov, Aleksandr, Gasnikov, Alexander

“… Motivated by applications in machine learning and beyond, stochastic methods are of great importance …”
Volltext

SARAH-M: A fast stochastic recursive gradient descent algorithm via momentum von Yang, Zhuang

“… However, the understanding of how the momentum improves the performance of modern variance reduced stochastic gradient algorithms, e.g …”
Volltext

Riemannian Stochastic Variance-Reduced Cubic Regularized Newton Method for Submanifold Optimization von Zhang, Dewei, Davanloo Tajbakhsh, Sam

“… We propose a stochastic variance-reduced cubic regularized Newton algorithm to optimize the finite-sum problem over a Riemannian submanifold of the Euclidean space …”
Volltext

Hybrid Acceleration Scheme for Variance Reduced Stochastic Optimization Algorithms von Sadeghi, Hamed, Giselsson, Pontus

“… To alleviate this problem, we propose an optimization algorithm -- which we refer to as a hybrid acceleration scheme -- for a class of proximal variance reduced stochastic optimization algorithms …”
Volltext