Stochastic Maximum Likelihood Optimization via Hypernetworks
Machine Learning
2018-01-15 v2 Machine Learning
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.
Cite
@article{arxiv.1712.01141,
title = {Stochastic Maximum Likelihood Optimization via Hypernetworks},
author = {Abdul-Saboor Sheikh and Kashif Rasul and Andreas Merentitis and Urs Bergmann},
journal= {arXiv preprint arXiv:1712.01141},
year = {2018}
}
Comments
To appear at NIPS 2017 Workshop on Bayesian Deep Learning