Publication Type

Working Paper

Version

publishedVersion

Publication Date

9-2021

Abstract

VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that could better aid the image classification tasks.

Discipline

Finance | Finance and Financial Management

Research Areas

Finance

First Page

1

Last Page

7

External URL

https://arxiv.org/abs/2109.14795

Share

COinS