In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
Authors
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro
Abstract
We present experiments demonstrating that some other form of capacity control, different from network size, plays a central role in learning multilayer feed-forward networks. We argue, partially through analogy to matrix factorization, that this is an inductive bias that can help shed light on deep learning.
