# Using Autoencoders and AutoDiff to Reconstruct Missing Variables in a Set of Time Series

arXiv: https://arxiv.org/abs/2308.10496 · HTML: https://mlsanity.com/paper/2308.10496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [An Introduction to Deep Generative Modeling](https://mlsanity.com/paper/2103.05180/) (2021)
- [Auxiliary Deep Generative Models](https://mlsanity.com/paper/1602.05473/) (2016)
- [Solving inverse problems using conditional invertible neural networks](https://mlsanity.com/paper/2007.15849/) (2020)
- [Time Series Data Imputation: A Survey on Deep Learning Approaches](https://mlsanity.com/paper/2011.11347/) (2020)
- [Universal approximation property of invertible neural networks](https://mlsanity.com/paper/2204.07415/) (2022)
- [Relational Autoencoder for Feature Extraction](https://mlsanity.com/paper/1802.03145/) (2018)
- [Fast Transient Simulation of High-Speed Channels Using Recurrent Neural Network](https://mlsanity.com/paper/1902.02627/) (2019)

## Abstract (arXiv)

Existing black box modeling approaches in machine learning suffer from a fixed input and output feature combination. In this paper, a new approach to reconstruct missing variables in a set of time series is presented. An autoencoder is trained as usual with every feature on both sides and the neural network parameters are fixed after this training. Then, the searched variables are defined as missing variables at the autoencoder input and optimized via automatic differentiation. This optimization is performed with respect to the available features loss calculation. With this method, different input and output feature combinations of the trained model can be realized by defining the searched variables as missing variables and reconstructing them. The combination can be changed without training the autoencoder again. The approach is evaluated on the base of a strongly nonlinear electrical component. It is working well for one of four variables missing and generally even for multiple missing variables.