Abstract:
Flow-based generative models are a family of generative models which enjoy the properties of tractable exact likelihood and efficient training and sampling. They are composed of a sequence of invertible functions. In this paper, we incorporate
matrix exponential into generative flows. Matrix exponential is a map from matrices to invertible matrices, this property is suitable for generative flows. Based on matrix exponential, we propose matrix exponential coupling layers which are a general case of affine coupling layers and a stable version of invertible 1 x 1 convolutions which do not collapse during training. And we modify the networks architecture to make training stable and significantly speed up the training process. Our experiments show that our model achieves great performance on density estimation amongst flow-based models.
