Mathematical Optimization for Machine Learning : Proceedings of the MATH+ Thematic Einstein Semester 2023 / / ed. by Martin Weiser, Aswin Kannan, Sebastian Pokutta, Kartikey Sharma, Daniel Walter, Andrea Walther, Konstantin Fackeldey

• Pubblicazione: Berlin ; ; Boston : , : De Gruyter, , [2025]; 2025
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (X, 202 p.)
• Soggetto topico: MATHEMATICS / Optimization
• Soggetto non controllato: Mathematical optimization, Machine learning, Nonlinear optimization, Discrete optimization, Physics informed learning
• Persona (resp. second.): BaumgärtnerLukas; BeecroftDamien; BethkeFranz; CaboussatAlexandre; CarlucciAntonio; ChewleSurahit; CotsOlivier; Cruz AlegríaSamuel A.; DuttoRémy; FackeldeyKonstantin; GaugerNicolas R.; GirardinMaude; GoseaIon Victor; GriewankAndreas; Grivet-TalociaStefano; HeinleinAlexander; HowardAmanda A.; JanSophie; KannanAswin; KopaničákováAlena; KrauseRolf; KreimeierTimo; LaporteSerge; PicassoMarco; PochampalliRohit; PokuttaSebastian; RabbenRobert Julian; SemlerPhillip; SharmaKartikey; ShyshkanovaGanna; SikorskiAlexander; SpiegelChristoph; StinisPanos; TointPh. L (Philippe L.); TrottiKen; Van HentenryckPascal; WalterDaniel; WaltherAndrea; WeberMarcus; WeiserMartin; WeiserMartin; ZimmerMax
• Nota di contenuto: Frontmatter -- Preface -- Acknowledgment -- Contents -- A framework to solve inverse problems for parametric PDEs using adaptive finite elements and neural networks -- Generation of value function data for bilevel optimal control and application to hybrid electric vehicle -- Graph neural networks to predict strokes from blood flow simulations -- Capturing the macroscopic behavior of molecular dynamics with membership functions -- Adaptive gradient-enhanced Gaussian process surrogates for inverse problems -- Multifidelity domain decomposition-based physics-informed neural networks and operators for time-dependent problems -- Constrained piecewise linear optimization by an active signature method -- Parallel trust-region approaches in neural network training -- Trustworthy optimization learning: a brief overview -- Compression-aware training of neural networks using Frank–Wolfe -- Approximation of generalized frequency response functions via vector fitting -- On the nonsmooth regularity condition LIKQ for different abs-normal representations -- Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example -- Index
• Sommario/riassunto: 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.
• Titolo autorizzato: Mathematical Optimization for Machine Learning
• ISBN: 3-11-137774-1; 3-11-137677-X
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911024074903321
• Lo trovi qui: Univ. Federico II
• Serie: De Gruyter Proceedings in Mathematics Series