.png){kind=icon}
Return
Accelerating Minibatch Stochastic Gradient Descent Using Typicality Sampling
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2019.2957003.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Machine learning, especially deep neural networks, has developed rapidly in fields, including computer vision, speech recognition, and reinforcement learning. Although minibatch stochastic gradient descent (SGD) is one of the most popular stochastic optimization methods for training deep networks, it shows a slow convergence rate due to the large noise in the gradient approximation. In this article, we attempt to remedy this problem by building a more efficient batch selection method based on typicality sampling, which reduces the error of gradient estimation in conventional minibatch SGD. We analyze the convergence rate of the resulting typical batch SGD algorithm and compare the convergence properties between the minibatch SGD and the algorithm. Experimental results demonstrate that our batch selection scheme works well and more complex minibatch SGD variants can benefit from the proposed batch selection strategy.
Keywords:
Training
Convergence
Approximation algorithms
Stochastic processes
Estimation
Optimization
Acceleration
Batch selection
machine learning
minibatch stochastic gradient descent (SGD)
speed of convergence
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
ShareSave
View more