.png){kind=icon}
返回
A stochastic conditional gradient algorithm for decentralized online convex optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jpdc.2022.07.010.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We study in this paper several problems at the intersection of decentralized optimization and online learning. Decentralized optimization plays a vital role in machine learning and has recently garnered much attention due to its inherent advantage in handling edge computations. Many decentralized optimization algorithms, both projection and projection-free algorithms with theoretical guarantees, have been proposed in the literature, focusing mainly on offline settings. However, for most real-world machine learning problems, the data is often revealed online, for example, in the case of recommender systems, image/video processing, and stock portfolio management. Therefore, in this work, we study decentralized optimization within the framework of online settings with constraints imposed on the optimization solutions (e.g., sparsity or low rank of matrices). More specifically, we consider the problem of optimizing an aggregate of convex loss functions that arrive over time such that their components are distributed over a connected network. We present a consensus-based online decentralized Frank-Wolfe algorithm that uses stochastic gradient estimates, which achieves an asymptotically tight regret guarantee of O(root T) where T is a given time horizon. Furthermore, we demonstrate the performance of this algorithm for optimizing the online multiclass logistic regression model on real-world standard image datasets (MNIST, CIFAR(10)) by comparing with centralized online algorithms. We achieve better regret bounds than the previously best-known decentralized constrained online algorithms. (C) 2022 Elsevier Inc. All rights reserved.
Keyword:
Online learning
Distributed learning
Edge computing
Machine learning
期刊
IF:
4
论文数:
3.8K
被引数:
4.8K
机构
引用论文
分享收藏Mechanism of Site-Specific Psoralen Photoadducts Formation in Triplex DNA Directed by Psoralen-Conjugated Oligonucleotides.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏
The physiological effects of cigarette smoking: Implications for psychophysiological research吸烟的生理效应: 对心理生理学研究的启示
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容