Database Alignment with Gaussian Features

Osman E. Dai, Daniel Cullina, Negar Kiyavash
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:3225-3233, 2019.

Abstract

We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual information between feature pairs, identifying the regimes where the algorithms are guaranteed to perform reliably and those where they cannot be expected to succeed.

Cite this Paper

BibTeX
@InProceedings{pmlr-v89-dai19b, title = {Database Alignment with Gaussian Features}, author = {Dai, Osman E. and Cullina, Daniel and Kiyavash, Negar}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {3225--3233}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/dai19b/dai19b.pdf}, url = {https://proceedings.mlr.press/v89/dai19b.html}, abstract = {We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual information between feature pairs, identifying the regimes where the algorithms are guaranteed to perform reliably and those where they cannot be expected to succeed.} }
Endnote
%0 Conference Paper %T Database Alignment with Gaussian Features %A Osman E. Dai %A Daniel Cullina %A Negar Kiyavash %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-dai19b %I PMLR %P 3225--3233 %U https://proceedings.mlr.press/v89/dai19b.html %V 89 %X We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual information between feature pairs, identifying the regimes where the algorithms are guaranteed to perform reliably and those where they cannot be expected to succeed.
APA
Dai, O.E., Cullina, D. & Kiyavash, N.. (2019). Database Alignment with Gaussian Features. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:3225-3233 Available from https://proceedings.mlr.press/v89/dai19b.html.

Related Material