English
Related papers

Related papers: Block Layer Decomposition schemes for training Dee…

200 papers

Training large language models typically demands extensive GPU memory and substantial financial investment, which poses a barrier for many small- to medium-sized teams. In this paper, we propose a full-parameter pre-training and fine-tuning…

Machine Learning · Computer Science 2025-09-29 Zeyu Liu , Yan Li , Yunquan Zhang , Boyang Zhang , Guoyong Jiang , Xin Zhang , Limin Xiao , Weifeng Zhang , Daning Cheng

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

Computer Vision and Pattern Recognition · Computer Science 2016-06-15 Maya Kabkab , Azadeh Alavi , Rama Chellappa

We propose the Block Coordinate Descent Network Simplex (BCDNS) method for solving large-scale discrete Optimal Transport (OT) problems. BCDNS integrates the Network Simplex (NS) algorithm with a block coordinate descent (BCD) strategy,…

Optimization and Control · Mathematics 2026-01-08 Lingrui Li , Nobuo Yamashita

In this paper, we propose Stochastic Block-ADMM as an approach to train deep neural networks in batch and online settings. Our method works by splitting neural networks into an arbitrary number of blocks and utilizes auxiliary variables to…

Machine Learning · Computer Science 2021-05-04 Saeed Khorram , Xiao Fu , Mohamad H. Danesh , Zhongang Qi , Li Fuxin

The stochastic gradient (SG) method can minimize an objective function composed of a large number of differentiable functions, or solve a stochastic optimization problem, to a moderate accuracy. The block coordinate descent/update (BCD)…

Optimization and Control · Mathematics 2015-11-23 Yangyang Xu , Wotao Yin

Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as compared to gradient-based approaches. We introduce a coordinate descent method…

Machine Learning · Computer Science 2020-06-19 Ravi G. Patel , Nathaniel A. Trask , Mamikon A. Gulian , Eric C. Cyr

We present a stochastic first-order optimization algorithm, named BCSC, that adds a cyclic constraint to stochastic block-coordinate descent. It uses different subsets of the data to update different subsets of the parameters, thus limiting…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Kensuke Nakamura , Stefano Soatto , Byung-Woo Hong

Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent…

Machine Learning · Computer Science 2022-03-03 Biyi Fang , Jean Utke , Diego Klabjan

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

Benders decomposition (BD) is a widely used solution approach for solving two-stage stochastic programs arising in real-world decision-making under uncertainty. However, it often suffers from slow convergence as the master problem grows…

Optimization and Control · Mathematics 2026-05-08 Haochen Cai , Xian Yu

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Machine Learning · Computer Science 2017-03-28 Sek Chai , Aswin Raghavan , David Zhang , Mohamed Amer , Tim Shields

Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its…

Machine Learning · Statistics 2017-12-18 Guangxi Li , Jinmian Ye , Haiqin Yang , Di Chen , Shuicheng Yan , Zenglin Xu

We study the worst-case behavior of Block Coordinate Descent (BCD) type algorithms for unconstrained minimization of coordinate-wise smooth convex functions. This behavior is indeed not completely understood, and the practical success of…

Optimization and Control · Mathematics 2025-07-23 Yassine Kamri , François Glineur , Julien M. Hendrickx , Ion Necoara

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However,…

Computer Vision and Pattern Recognition · Computer Science 2018-03-01 Guangrun Wang , Jiefeng Peng , Ping Luo , Xinjiang Wang , Liang Lin

In this paper we present a novel randomized block coordinate descent method for the minimization of a convex composite objective function. The method uses (approximate) partial second-order (curvature) information, so that the algorithm…

Optimization and Control · Mathematics 2015-05-11 Kimon Fountoulakis , Rachael Tappenden

Training of deep neural networks (DNNs) frequently involves optimizing several millions or even billions of parameters. Even with modern computing architectures, the computational expense of DNN training can inhibit, for instance, network…

Machine Learning · Computer Science 2020-06-26 Mauricio E. Tano , Gavin D. Portwood , Jean C. Ragusa

Block coordinate descent is an optimization paradigm that iteratively updates one block of variables at a time, making it quite amenable to big data applications due to its scalability and performance. Its convergence behavior has been…

Optimization and Control · Mathematics 2023-10-13 Liangzu Peng , René Vidal

Block-coordinate descent (BCD) is a popular framework for large-scale regularized optimization problems with block-separable structure. Existing methods have several limitations. They often assume that subproblems can be solved exactly at…

Optimization and Control · Mathematics 2019-11-05 Ching-pei Lee , Stephen J. Wright

There are two main streams in up-to-date image denoising algorithms: non-local self similarity (NSS) prior based methods and convolutional neural network (CNN) based methods. The NSS based methods are favorable on images with regular and…

Computer Vision and Pattern Recognition · Computer Science 2017-04-04 Byeongyong Ahn , Nam Ik Cho

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada