2018
DOI: 10.1016/j.neucom.2017.11.044
|View full text |Cite
|
Sign up to set email alerts
|

Distributed and asynchronous Stochastic Gradient Descent with variance reduction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
1
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 20 publications
(5 citation statements)
references
References 6 publications
0
1
0
Order By: Relevance
“…The RS-DCNN approach primarily implements two steps: (1) preparation of the training dataset which is done by dividing large RS satellite images into smaller images and then, implementing an algorithm called Maximum Likelihood which is a supervised classification algorithm (2) A distributed CNN algorithm is applied to carry out accurate classification of the big satellite images. For bringing in parallelism for image classification, the Asynchronous Distributed Stochastic Gradient Descent (ADSGD) algorithm [24] is used which distributes the execution of the CNN algorithm across the entire big data cluster.…”
Section: Rs-dcnn: Distributed Cnn To Classify Remote Sensing Imagesmentioning
confidence: 99%
“…The RS-DCNN approach primarily implements two steps: (1) preparation of the training dataset which is done by dividing large RS satellite images into smaller images and then, implementing an algorithm called Maximum Likelihood which is a supervised classification algorithm (2) A distributed CNN algorithm is applied to carry out accurate classification of the big satellite images. For bringing in parallelism for image classification, the Asynchronous Distributed Stochastic Gradient Descent (ADSGD) algorithm [24] is used which distributes the execution of the CNN algorithm across the entire big data cluster.…”
Section: Rs-dcnn: Distributed Cnn To Classify Remote Sensing Imagesmentioning
confidence: 99%
“…The determination of confidence regions and a stopping criterion are based on information from iteration and advantage in priori rules. The stochastic approximation method is an iteration method that uses the function of estimates to find the function root [39][40][41][42][43].…”
Section: Projected Stochastic Gradient (Psg)mentioning
confidence: 99%
“…The SGD algorithm has been demonstrated to be very useful in training a variety of DNNs. Some related works have been proposed to speed up the efficiency of the SGD training through the parallel and distributed training [15,16]. Hogwild!…”
Section: Related Workmentioning
confidence: 99%