Stochastic Maximum Likelihood Optimization via Hypernetworks

Abstract

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given input. Using this approach we obtain competitive empirical results on regression and classification benchmarks.

Publication
NeurIPS 2017 Workshop on Bayesian Deep Learning
Date
Links
PDF