In this paper, we propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows. The proposed model is capable of mapping any partial data to a multi-modal latent variational distribution. Sampling from such a distribution leads to stochastic imputation. Preliminary evaluation on MNIST dataset shows promising stochastic imputation conditioned on partial images as input.
Bibtex
@InProceedings{Carvahlo2019,
title ={{Arbitrarily-conditioned Data Imputation}},
author ={Carvalho, Micael and Durand, Thibaut and He, Jiawei and Mehrasa, Nazanin and Mori, Greg},
booktitle ={Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference},
year ={2019},
url = {https://openreview.net/forum?id=r1eP5khVKB},
Related Research
-
ACL 2023 Recommended Reading List
ACL 2023 Recommended Reading List
P. Forsyth, K. Tang, and W. Zi.
Research
-
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
K. Arora, L. El Asri, H. Bahuleyan, and J. Chi Kit Cheung. Association for Computational Linguistics (ACL)
Publications