StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
Machine Learning
2021-01-08 v1 Artificial Intelligence
Machine Learning
Abstract
In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable properties: 1) training requires no gradient as solution to the system of linear equations is not stochastic, 2) is highly scalable when solving the system of linear equations w.r.t the latent codes, and similarly for the parameters of the model, and 3) it gives desirable least-square bounds for the estimation of latent codes and network parameters within each layer.
Cite
@article{arxiv.2101.00574,
title = {StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations},
author = {Amir Zadeh and Santiago Benoit and Louis-Philippe Morency},
journal= {arXiv preprint arXiv:2101.00574},
year = {2021}
}
Comments
Work in progress at CMU