Optimization Methods For Large-Scale Machine Learning

This paper mainly completes the binary classification of RCV1 text data set by logistic regression. Based on the established logistic regression model, the performance and characteristics of three numerical optimization algorithms-random gradient descent, Mini-Batch random gradient and L-BFGS are st...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) (Online) s. 304 - 308
Hlavní autoři: Gao, Yuan, Li, Jianping, Zhou, Yue, Xiao, Fei, Liu, He
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 17.12.2021
Témata:
Information processing
L-BFGS
Logistic regression
Machine learning
Machine learning algorithms
Media
Mini-Batch random gradient
Numerical models
Optimization methods
Parallel processing
ISSN:2576-8964
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper mainly completes the binary classification of RCV1 text data set by logistic regression. Based on the established logistic regression model, the performance and characteristics of three numerical optimization algorithms-random gradient descent, Mini-Batch random gradient and L-BFGS are studied.
ISSN:2576-8964
DOI:10.1109/ICCWAMTIP53232.2021.9674150