.png){kind=icon}
.png){kind=icon}
Return
Accelerated First-Order Optimization Algorithms for Machine Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/JPROC.2020.3007634.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Numerical optimization serves as one of the pillars of machine learning. To meet the demands of big data applications, lots of efforts have been put on designing theoretically and practically fast algorithms. This article provides a comprehensive survey on accelerated first-order algorithms with a focus on stochastic algorithms. Specifically, this article starts with reviewing the basic accelerated algorithms on deterministic convex optimization, then concentrates on their extensions to stochastic convex optimization, and at last introduces some recent developments on acceleration for nonconvex optimization.
Keywords:
Numerical analysis
Machine learning algorithms
Optimization methods
Machine learning
Convergence
Complexity theory
Approximation algorithms
Convex functions
Acceleration
convex optimization
deterministic algorithms
machine learning
nonconvex optimization
stochastic algorithms
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
25.9
Papers:
9.9K
Citations:
4.5W
View more organizations