Generative Flows with Matrix Exponential
This work is incremental, enhancing generative flow models for researchers in machine learning by addressing training stability and speed.
The authors tackled the problem of improving generative flow models by incorporating matrix exponential to create more stable and efficient invertible layers, resulting in great performance on density estimation tasks.
Generative flows models enjoy the properties of tractable exact likelihood and efficient sampling, which 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 that are a general case of affine coupling layers and matrix exponential invertible 1 x 1 convolutions that do not collapse during training. And we modify the networks architecture to make trainingstable andsignificantly speed up the training process. Our experiments show that our model achieves great performance on density estimation amongst generative flows models.