Variational Recurrent Auto-Encoders

TL;DR

This paper introduces the Variational Recurrent Auto-Encoder (VRAE), a model combining RNNs and variational inference for scalable, unsupervised learning and generation of time series data, leveraging unlabeled data for improved training.

Contribution

The paper presents a novel VRAE model that integrates RNNs with variational auto-encoders, enabling efficient large-scale unsupervised learning and data generation for time series.

Findings

Effective latent representations for time series

Generates realistic synthetic data

Utilizes unlabeled data to enhance supervised training

Abstract

In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that data can be generated from samples of the latent space. An important contribution of this work is that the model can make use of unlabeled data in order to facilitate supervised training of RNNs by initialising the weights and network state.