First-order and Stochastic Optimization Methods for Machine Learning / Guanghui Lan

• Autore: Lan, Guanghui
• Pubblicazione: Cham, : Springer, 2020
• Titolo uniforme: First-order and Stochastic Optimization Methods for Machine Learning
• Descrizione fisica: xiii, 582 p. : ill. ; 24 cm
• Soggetto topico: 68-XX - Computer science [MSC 2020]; 90C25 - Convex programming [MSC 2020]; 90C15 - Stochastic programming [MSC 2020]; 68W15 - Distributed algorithms [MSC 2020]; 68T05 - Learning and adaptive systems in artificial intelligence [MSC 2020]; 90C26 - Nonconvex programming, global optimization [MSC 2020]; 68W20 - Randomized algorithms [MSC 2020]; 68W27 - Online algorithms; streaming algorithms [MSC 2020]
• Soggetto non controllato: Distributed and decentralized methods; Machine learning algorithms; Nonconvex optimization methods; Randomized algorithms; Stochastic optimization methods
• Titolo autorizzato: First-order and Stochastic Optimization Methods for Machine Learning
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: VAN0249143
• Lo trovi qui: Univ. Vanvitelli
• Localizzazioni e accesso elettronico: http://doi.org/10.1007/978-3-030-39568-1
• Serie: Springer series in the Data Sciences Berlin [etc.] . -Springer