Optimization Algorithms Articles

Page 1 of 1 (1 article)

4/1/2021 • EN

Notes on the Origin of Implicit Regularization in SGD

Explores how Stochastic Gradient Descent (SGD) inherently prefers certain minima, leading to better generalization in deep learning, beyond classical theory.

Deep Learning Generalization Implicit Regularization Optimization Algorithms Stochastic Gradient Descent

Ferenc Huszár

Optimization Algorithms Articles

Notes on the Origin of Implicit Regularization in SGD

Select Language