Can Auto-Encoders Help with Filling Missing Data?
Abstract
This paper introduces an approach to filling in missing data based on deep auto-encoder models, adequate to high-dimensional data exhibiting complex dependencies, such as images. The method exploits the properties of auto-encoders' vector fields, which allows to approximate the gradient of the log-density from its reconstruction error, based on which we propose a projected gradient ascent algorithm to obtain the conditionally most probable estimate of the missing values. Experiments performed on benchmark datasets show that imputations produced by our model are sharp and realistic.
Cite
Text
Śmieja et al. "Can Auto-Encoders Help with Filling Missing Data?." ICLR 2020 Workshops: DeepDiffEq, 2020.Markdown
[Śmieja et al. "Can Auto-Encoders Help with Filling Missing Data?." ICLR 2020 Workshops: DeepDiffEq, 2020.](https://mlanthology.org/iclrw/2020/smieja2020iclrw-autoencoders/)BibTeX
@inproceedings{smieja2020iclrw-autoencoders,
title = {{Can Auto-Encoders Help with Filling Missing Data?}},
author = {Śmieja, Marek and Kołomycki, Maciej and Struski, Łukasz and Juda, Mateusz and Figueiredo, Mário A. T.},
booktitle = {ICLR 2020 Workshops: DeepDiffEq},
year = {2020},
url = {https://mlanthology.org/iclrw/2020/smieja2020iclrw-autoencoders/}
}