Book
Open Access
Mathematical Optimization for Machine Learning
Proceedings of the MATH+ Thematic Einstein Semester 2023
-
Edited by:
Konstantin Fackeldey
Language:
English
Published/Copyright:
2025
About this book
Mathematical optimization and machine learning are closely related. This proceedings volume of the Thematic Einstein Semester 2023 of the Berlin Mathematics Research Center MATH+ collects recent progress on their interplay in topics such as discrete optimization, nonlinear programming, optimal control, first-order methods, multilevel optimization, machine learning in optimization, physics-informed learning, and fairness in machine learning.
- Focuses on the interplay of optimization and machine learning.
- Includes bidirectional relation: ML as optimization and accelerating optimization by ML.
- Provides a broad overview of recent progress in this combination.
Author / Editor information
M. Weiser, S. Pokutta, K. Sharma, ZIB, Germany; K. Fackeldey, TU Berlin; A. Kannan, D. Walter, A. Walther, Humboldt-Univ. Germany.
Topics
-
Download PDFOpen Access
Frontmatter
I -
Download PDFOpen Access
Preface
V -
Download PDFOpen Access
Acknowledgment
VII -
Download PDFOpen Access
Contents
IX -
Download PDFOpen Access
A framework to solve inverse problems for parametric PDEs using adaptive finite elements and neural networks
1 -
Download PDFOpen Access
Generation of value function data for bilevel optimal control and application to hybrid electric vehicle
17 -
Download PDFOpen Access
Graph neural networks to predict strokes from blood flow simulations
29 -
Download PDFOpen Access
Capturing the macroscopic behavior of molecular dynamics with membership functions
41 -
Download PDFOpen Access
Adaptive gradient-enhanced Gaussian process surrogates for inverse problems
59 -
Download PDFOpen Access
Multifidelity domain decomposition-based physics-informed neural networks and operators for time-dependent problems
79 -
Download PDFOpen Access
Constrained piecewise linear optimization by an active signature method
93 -
Download PDFOpen Access
Parallel trust-region approaches in neural network training
107 -
Download PDFOpen Access
Trustworthy optimization learning: a brief overview
121 -
Download PDFOpen Access
Compression-aware training of neural networks using Frank–Wolfe
137 -
Download PDFOpen Access
Approximation of generalized frequency response functions via vector fitting
169 -
Download PDFOpen Access
On the nonsmooth regularity condition LIKQ for different abs-normal representations
181 -
Download PDFOpen Access
Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example
195 -
Download PDFOpen Access
Index
199
Publishing information
Pages and Images/Illustrations in book
eBook published on:
May 6, 2025
eBook ISBN:
9783111376776
Hardcover published on:
May 6, 2025
Hardcover ISBN:
9783111375854
Pages and Images/Illustrations in book
Front matter:
10
Main content:
202
Illustrations:
2
Coloured Illustrations:
53
Tables:
27
Keywords for this book
Mathematical optimization; Machine learning; Nonlinear optimization; Discrete optimization; Physics informed learning
Audience(s) for this book
Researchers, practitioners and PhD students, interested in machine learning and mathematical optimization.
Creative Commons
BY-ND 4.0
Safety & product resources
-
Manufacturer information:
Walter de Gruyter GmbH
Genthiner Straße 13
10785 Berlin
productsafety@degruyterbrill.com
