Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning

Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning

The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses, we introduce variational characterizations that naturally suggest a two-step scheme...

Full description

Bibliographic Details
Main Authors: Nicolas García Trillos, Zachary Kaplan, Daniel Sanz-Alonso
Format: Article
Language:English
Published: MDPI AG 2019-05-01
Series:Entropy
Subjects:
deep learning
local entropy
heat regularization
variational characterizations
Kullback–Leibler approximations
monotonic training
Online Access:https://www.mdpi.com/1099-4300/21/5/511

Internet

https://www.mdpi.com/1099-4300/21/5/511

Similar Items