Approximate Inference in Structured Instances with Noisy Categorical Observations
Alireza Heidari, Ihab F. Ilyas, Theodoros Rekatsinas
Abstract
We study the problem of recovering the latent ground truth labeling of a structured instance with categorical random variables in the presence of noisy observations. We present a new approximate algorithm for graphs with categorical variables that achieves low Hamming error in the presence of noisy vertex and edge observations. Our main result shows a logarithmic dependency of the Hamming error to the number of categories of the random variables. Our approach draws connections to correlation clustering with a fixed number of clusters. Our results generalize the works of Globerson et al. (2015) and Foster et al. (2018), who study the hardness of structured prediction under binary labels, to the case of categorical labels.
BibTeX
@InProceedings{pmlr-v115-heidari20a,
title = {Approximate Inference in Structured Instances with Noisy Categorical Observations},
author = {Heidari, Alireza and Ilyas, Ihab F. and Rekatsinas, Theodoros},
booktitle = {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference},
pages = {412--421},
year = {2020},
editor = {Adams, Ryan P. and Gogate, Vibhav},
volume = {115},
series = {Proceedings of Machine Learning Research},
month = {22--25 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v115/heidari20a/heidari20a.pdf},
url = {https://proceedings.mlr.press/v115/heidari20a.html},
abstract = {We study the problem of recovering the latent ground truth labeling of a structured instance with categorical random variables in the presence of noisy observations. We present a new approximate algorithm for graphs with categorical variables that achieves low Hamming error in the presence of noisy vertex and edge observations. Our main result shows a logarithmic dependency of the Hamming error to the number of categories of the random variables. Our approach draws connections to correlation clustering with a fixed number of clusters. Our results generalize the works of Globerson et al. (2015) and Foster et al. (2018), who study the hardness of structured prediction under binary labels, to the case of categorical labels.}
}