Database Alignment with Gaussian Features

Osman Emre Dai; Daniel Cullina; Negar Kiyavash

Database Alignment with Gaussian Features

Osman Emre Dai
, Daniel Cullina
, Negar Kiyavash

Electrical Engineering

Research output: Contribution to journal › Conference article › peer-review

2 Scopus citations

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.

Original language	English (US)
Pages (from-to)	3225-3233
Number of pages	9
Journal	Proceedings of Machine Learning Research
Volume	89
State	Published - 2019
Event	22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan Duration: Apr 16 2019 → Apr 18 2019

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Statistics and Probability
Artificial Intelligence

Cite this

@article{57627dbda5be4f1c8960d6aca4e5e5ae,

title = "Database Alignment with Gaussian Features",

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.",

author = "Dai, \{Osman Emre\} and Daniel Cullina and Negar Kiyavash",

note = "Publisher Copyright: {\textcopyright} 2019 by the author(s).; 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 ; Conference date: 16-04-2019 Through 18-04-2019",

year = "2019",

language = "English (US)",

volume = "89",

pages = "3225--3233",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Database Alignment with Gaussian Features

AU - Dai, Osman Emre

AU - Cullina, Daniel

AU - Kiyavash, Negar

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/105020736302

UR - https://www.scopus.com/pages/publications/105020736302#tab=citedBy

M3 - Conference article

AN - SCOPUS:105020736302

SN - 2640-3498

VL - 89

SP - 3225

EP - 3233

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019

Y2 - 16 April 2019 through 18 April 2019

ER -

Database Alignment with Gaussian Features

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this