Suchergebnisse - block‐coordinate gradient descent algorithm

A novel block‐coordinate gradient descent algorithm for simultaneous grouped selection of fixed and random effects in joint modeling von Chen, Shuyan, Fang, Zhiqing, Li, Zhong, Liu, Xin

“… In this article, we propose a novel block‐coordinate gradient descent (BCGD) algorithm to simultaneously select multiple longitudinal covariates that may carry …”
Volltext

Convergence of Gradient-Based Block Coordinate Descent Algorithms for Nonorthogonal Joint Approximate Diagonalization of Matrices von Li, Jianze, Usevich, Konstantin, Comon, Pierre

Volltext

Convergence of gradient-based block coordinate descent algorithms for non-orthogonal joint approximate diagonalization of matrices von Li, Jianze, Usevich, Konstantin, Comon, Pierre

“… In this paper, we propose a gradient based block coordinate descent (BCD-G) framework to solve the joint approximate diagonalization of matrices defined on the product of the complex Stiefel manifold and the special linear group …”
Volltext

A Block Coordinate Descent-Based Projected Gradient Algorithm for Orthogonal Non-Negative Matrix Factorization von Asadi, Soodabeh, Povh, Janez

“… ), where one or both matrix factors must have orthonormal columns or rows. We penalize the orthonormality constraints and apply the PG method via a block coordinate descent approach …”
Volltext

Iteration complexity analysis of block coordinate descent methods von Hong, Mingyi, Wang, Xiangfeng, Razaviyayn, Meisam, Luo, Zhi-Quan

“… In this paper, we provide a unified iteration complexity analysis for a family of general block coordinate descent methods, covering popular methods such as the block coordinate gradient descent …”
Volltext

An Improved Adam Optimization Algorithm Combining Adaptive Coefficients and Composite Gradients Based on Randomized Block Coordinate Descent von Liu, Miaomiao, Yao, Dan, Liu, Zhigang, Guo, Jingfeng, Chen, Jing

“… An improved Adam optimization algorithm combining adaptive coefficients and composite gradients based on randomized block coordinate descent is proposed to address issues of the Adam algorithm …”
Volltext

Structured feature selection using coordinate descent optimization von Ghalwash, Mohamed F., Cao, Xi Hang, Stojkovic, Ivan, Obradovic, Zoran

“… optimization problems so that the problem can be solved by any standard optimization algorithm …”
Volltext

Convergence of gradient-based block coordinate descent algorithms for non-orthogonal joint approximate diagonalization of matrices von Li, Jianze, Usevich, Konstantin, Comon, Pierre

“… In this paper, we propose a gradient-based block coordinate descent (BCD-G) framework to solve the joint approximate diagonalization of matrices defined on the product of the complex Stiefel manifold and the special linear group …”
Volltext

A Local Block Coordinate Descent Algorithm for the CSC Model von Zisselman, Ev, Sulam, Jeremias, Elad, Michael

“… In this work we propose a new and simple approach that adopts a localized strategy, based on the Block Coordinate Descent algorithm …”
Volltext

A Block Coordinate Descent-based Projected Gradient Algorithm for Orthogonal Non-negative Matrix Factorization von Asadi, Soodabeh, Povh, Janez

“… ), where one or both matrix factors must have orthonormal columns or rows. We penalise the orthonormality constraints and apply the PG method via a block coordinate descent approach …”
Volltext

Robust Low-Rank Tensor Recovery With Regularized Redescending M-Estimator von Yuning Yang, Yunlong Feng, Suykens, Johan A. K.

“… This paper addresses the robust low-rank tensor recovery problems. Tensor recovery aims at reconstructing a low-rank tensor from some linear measurements, …”
Volltext

Low-rank matrix factorization with nonconvex regularization and bilinear decomposition von Wang, Sijie, Xia, Kewen, Wang, Li, Yin, Zhixian, He, Ziping, Zhang, Jiangnan, Aslam, Naila

“… •A non-convex bilinear low-rank matrix factorization model is proposed.•A block coordinate descent based algorithm is derived with convergence conditions …”
Volltext

Online Learning for DNN Training: A Stochastic Block Adaptive Gradient Algorithm von Liu, Jianghui, Li, Baozhu, Zhou, Yangfan, Zhao, Xuhui, Zhu, Junlong, Zhang, Mingchuan

“… In this algorithm, stochastic block coordinate descent and the adaptive learning rate are utilized at each iteration …”
Volltext

Direct Optimization of the Dictionary Learning Problem von Rakotomamonjy, Alain

“… The algorithm we advocate simply performs a joint proximal gradient descent step over the dictionary atoms and the coefficient matrix …”
Volltext

FedBCD: A Communication-Efficient Collaborative Learning Framework for Distributed Features von Liu, Yang, Zhang, Xinwei, Kang, Yan, Li, Liping, Chen, Tianjian, Hong, Mingyi, Yang, Qiang

“… over sharing such messages during learning. We propose a Federated Stochastic Block Coordinate Descent (FedBCD …”
Volltext

Distributed algorithms for computing a fixed point of multi-agent nonexpansive operators von Li, Xiuxian, Xie, Lihua

“… To solve the problem, two algorithms are developed, called distributed Krasnosel’skiĭ–Mann (D-KM) and distributed block-coordinate …”
Volltext

Asynchronous incremental block-coordinate descent von Aytekin, Arda, Feyzmahdavian, Hamid Reza, Johansson, Mikael

“… In our algorithm, a coordinator updates a global iterate based on delayed partial gradients of the individual objective functions with respect to blocks of coordinates …”
Volltext

Stochastic Augmented Projected Gradient Methods for the Large-Scale Precoding Matrix Indicator Selection Problem von Zhang, Jiaqi, Jin, Zeyu, Jiang, Bo, Wen, Zaiwen

“… The discrete constraints in the formulations make the problem NP-hard. Then we propose a stochastic projected gradient method augmented by block coordinate descent under various strategies …”
Volltext

Inexact Block Coordinate Descent Algorithms for Nonsmooth Nonconvex Optimization von Yang, Yang, Pesavento, Marius, Luo, Zhi-Quan, Ottersten, Bjorn

“… In this paper, we propose an inexact block coordinate descent algorithm for large-scale nonsmooth nonconvex optimization problems …”
Volltext

A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion von Xu, Yangyang, Yin, Wotao

“… We review some interesting applications and propose a generalized block coordinate descent method …”
Volltext