Stabilizing Invertible Neural Networks Using Mixture Models
Machine Learning
2021-09-01 v2 Optimization and Control
Machine Learning
Abstract
In this paper, we analyze the properties of invertible neural networks, which provide a way of solving inverse problems. Our main focus lies on investigating and controlling the Lipschitz constants of the corresponding inverse networks. Without such an control, numerical simulations are prone to errors and not much is gained against traditional approaches. Fortunately, our analysis indicates that changing the latent distribution from a standard normal one to a Gaussian mixture model resolves the issue of exploding Lipschitz constants. Indeed, numerical simulations confirm that this modification leads to significantly improved sampling quality in multimodal applications.
Cite
@article{arxiv.2009.02994,
title = {Stabilizing Invertible Neural Networks Using Mixture Models},
author = {Paul Hagemann and Sebastian Neumayer},
journal= {arXiv preprint arXiv:2009.02994},
year = {2021}
}