Deep relaxation: partial differential equations for optimizing deep neural networks

Entropy-SGD is a first-order optimization method which has been used successfully to train deep neural networks. This algorithm, which was motivated by statistical physics, is now interpreted as gradient descent on a modified loss function. The modified, or relaxed, loss function is the solution of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Research in the mathematical sciences 2018-09, Vol.5 (3), p.1-30, Article 30
Hauptverfasser:	Chaudhari, Pratik, Oberman, Adam, Osher, Stanley, Soatto, Stefano, Carlier, Guillaume
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Applications of Mathematics Artificial neural networks Computational Mathematics and Numerical Analysis Convergence Empirical analysis Mathematics Mathematics and Statistics Neural networks Optimal control Optimization Partial differential equations Stochastic processes
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!