Proximal Mapping for Deep Regularization

NIPS 2020, 2020.

Cited by: 0|Views14
EI
Weibo:
We proposed using proximal mapping as a new primitive in deep networks to explicitly encode the prior for end-to-end training

Abstract:

Underpinning the success of deep learning is effective regularizations that allow a variety of priors in data to be modeled. For example, robustness to adversarial perturbations, and correlations between multiple modalities. However, most regularizers are specified in terms of hidden layer outputs, which are not themselves optimization ...More
Your rating :
0

 

Tags
Comments