國立高雄大學圖資館 |

Language: English

Back

Accelerated optimization for machine...

Fang, Cong.

Accelerated optimization for machine learningfirst-order algorithms /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Accelerated optimization for machine learningby Zhouchen Lin, Huan Li, Cong Fang.
Reminder of title:	first-order algorithms /
Author:	Lin, Zhouchen.
other author:	Li, Huan.
Published:	Singapore :Springer Singapore :2020.
Description:	xxiv, 275 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Machine learningMathematics.
Online resource:	https://doi.org/10.1007/978-981-15-2910-8
ISBN:	9789811529108$q(electronic bk.)

Accelerated optimization for machine learningfirst-order algorithms /
Lin, Zhouchen.

Accelerated optimization for machine learningfirst-order algorithms /[electronic resource] :by Zhouchen Lin, Huan Li, Cong Fang. - Singapore :Springer Singapore :2020. - xxiv, 275 p. :ill., digital ;24 cm.

Chapter 1. Introduction -- Chapter 2. Accelerated Algorithms for Unconstrained Convex Optimization -- Chapter 3. Accelerated Algorithms for Constrained Convex Optimization -- Chapter 4. Accelerated Algorithms for Nonconvex Optimization -- Chapter 5. Accelerated Stochastic Algorithms -- Chapter 6. Accelerated Paralleling Algorithms -- Chapter 7. Conclusions.

This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on optimization to solve problems with its learning models, and first-order optimization algorithms are the mainstream approaches. The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning. Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning. It discusses a variety of methods, including deterministic and stochastic algorithms, where the algorithms can be synchronous or asynchronous, for unconstrained and constrained problems, which can be convex or non-convex. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference resource for users who are seeking faster optimization algorithms, as well as for graduate students and researchers wanting to grasp the frontiers of optimization in machine learning in a short time.

ISBN: 9789811529108$q(electronic bk.)

Standard No.: 10.1007/978-981-15-2910-8doiSubjects--Topical Terms:

857106
Machine learning
--Mathematics.

LC Class. No.: Q325.5 / .L569 2020

Dewey Class. No.: 006.310151

Accelerated optimization for machine learningfirst-order algorithms /
LDR:02414nmm a2200325 a 4500 001 579515
003 DE-He213
005 20200529181313.0
006 m
007 cr
008 201229s2020
020 $a 9789811529108$q(electronic bk.)
020 $a 9789811529092$q(paper)
024 7 $a 10.1007/978-981-15-2910-8 $2 doi
035 $a 978-981-15-2910-8
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5 $b .L569 2020
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.310151 $2 23
090 $a Q325.5 $b .L735 2020
100 1 $a Lin, Zhouchen. $3 853539
245 1 0 $a Accelerated optimization for machine learning $h [electronic resource] : $b first-order algorithms / $c by Zhouchen Lin, Huan Li, Cong Fang.
260 $a Singapore : $b Springer Singapore : $b Imprint: Springer, $c 2020.
300 $a xxiv, 275 p. : $b ill., digital ; $c 24 cm.
505 0 $a Chapter 1. Introduction -- Chapter 2. Accelerated Algorithms for Unconstrained Convex Optimization -- Chapter 3. Accelerated Algorithms for Constrained Convex Optimization -- Chapter 4. Accelerated Algorithms for Nonconvex Optimization -- Chapter 5. Accelerated Stochastic Algorithms -- Chapter 6. Accelerated Paralleling Algorithms -- Chapter 7. Conclusions.
520 $a This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on optimization to solve problems with its learning models, and first-order optimization algorithms are the mainstream approaches. The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning. Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning. It discusses a variety of methods, including deterministic and stochastic algorithms, where the algorithms can be synchronous or asynchronous, for unconstrained and constrained problems, which can be convex or non-convex. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference resource for users who are seeking faster optimization algorithms, as well as for graduate students and researchers wanting to grasp the frontiers of optimization in machine learning in a short time.
650 0 $a Machine learning $x Mathematics. $3 857106
650 0 $a Mathematical optimization. $3 183292
650 1 4 $a Machine Learning. $3 833608
650 2 4 $a Optimization. $3 274084
650 2 4 $a Math Applications in Computer Science. $3 273991
650 2 4 $a Computational Mathematics and Numerical Analysis. $3 274020
700 1 $a Li, Huan. $3 868900
700 1 $a Fang, Cong. $3 868901
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
856 4 0 $u https://doi.org/10.1007/978-981-15-2910-8
950 $a Computer Science (Springer-11645)