國立高雄大學圖資館 |

Language: English

Back

Variational and information flows in machine learning and optimal transport

Record Type:	Electronic resources : Monograph/item
Title/Author:	Variational and information flows in machine learning and optimal transportby Wuchen Li ... [et al.].
other author:	Li, Wuchen.
Published:	Cham :Springer Nature Switzerland :2025.
Description:	xiv, 254 p. :ill. (some col.), digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Stochastic processes.
Online resource:	https://doi.org/10.1007/978-3-031-92731-7
ISBN:	9783031927317$q(electronic bk.)

Variational and information flows in machine learning and optimal transport
Variational and information flows in machine learning and optimal transport[electronic resource] /by Wuchen Li ... [et al.]. - Cham :Springer Nature Switzerland :2025. - xiv, 254 p. :ill. (some col.), digital ;24 cm. - Oberwolfach seminars,v. 562296-5041 ;. - Oberwolfach seminars ;44..

- 1. A Dynamic Perspective of Optimal Transport -- 2. A Geometric Perspective on Diffeomorphic and Optimal Transport Flows and Their Applications -- 3. Wasserstein Dynamics in Mathematical Data Sciences -- 4. Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans.

This book is based on lectures given at the Mathematisches Forschungsinstitut Oberwolfach on "Computational Variational Flows in Machine Learning and Optimal Transport". Variational and stochastic flows on measure spaces are ubiquitous in machine learning and generative modeling. Optimal transport and diffeomorphic flows provide powerful frameworks to analyze such trajectories of distributions with elegant notions from differential geometry, such as geodesics, gradient and Hamiltonian flows. Recently, mean field control and mean field games offered a general optimal control variational view on learning problems. The four independent chapters in this book address the question of how the presented tools lead us to better understanding and further development of machine learning and generative models.

ISBN: 9783031927317$q(electronic bk.)

Standard No.: 10.1007/978-3-031-92731-7doiSubjects--Topical Terms:

181874
Stochastic processes.

LC Class. No.: QA274

Dewey Class. No.: 519.23

Variational and information flows in machine learning and optimal transport
LDR:02160nmm a2200337 a 4500 001 682832
003 DE-He213
005 20250718130247.0
006 m d
007 cr nn 008maaau
008 251209s2025 sz s 0 eng d
020 $a 9783031927317$q(electronic bk.)
020 $a 9783031927300$q(paper)
024 7 $a 10.1007/978-3-031-92731-7 $2 doi
035 $a 978-3-031-92731-7
040 $a GP $c GP
041 0 $a eng
050 4 $a QA274
072 7 $a PBKJ $2 bicssc
072 7 $a MAT007000 $2 bisacsh
072 7 $a PBKJ $2 thema
082 0 4 $a 519.23 $2 23
090 $a QA274 $b .V299 2025
245 0 0 $a Variational and information flows in machine learning and optimal transport $h [electronic resource] / $c by Wuchen Li ... [et al.].
260 $a Cham : $b Springer Nature Switzerland : $b Imprint: Birkhäuser, $c 2025.
300 $a xiv, 254 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a Oberwolfach seminars, $x 2296-5041 ; $v v. 56
505 0 $a - 1. A Dynamic Perspective of Optimal Transport -- 2. A Geometric Perspective on Diffeomorphic and Optimal Transport Flows and Their Applications -- 3. Wasserstein Dynamics in Mathematical Data Sciences -- 4. Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans.
520 $a This book is based on lectures given at the Mathematisches Forschungsinstitut Oberwolfach on "Computational Variational Flows in Machine Learning and Optimal Transport". Variational and stochastic flows on measure spaces are ubiquitous in machine learning and generative modeling. Optimal transport and diffeomorphic flows provide powerful frameworks to analyze such trajectories of distributions with elegant notions from differential geometry, such as geodesics, gradient and Hamiltonian flows. Recently, mean field control and mean field games offered a general optimal control variational view on learning problems. The four independent chapters in this book address the question of how the presented tools lead us to better understanding and further development of machine learning and generative models.
650 0 $a Stochastic processes. $3 181874
650 0 $a Computational intelligence. $3 210824
650 0 $a Machine learning $x Mathematics. $3 857106
650 1 4 $a Differential Equations. $3 285983
650 2 4 $a Calculus of Variations and Optimization. $3 913393
700 1 $a Li, Wuchen. $3 996655
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Oberwolfach seminars ; $v 44. $3 683269
856 4 0 $u https://doi.org/10.1007/978-3-031-92731-7
950 $a Mathematics and Statistics (SpringerNature-11649)