Hierarchical clustering with optimal transport

被引：23

作者：

Chakraborty, Saptarshi ^{[1
]}

Paul, Debolina ^{[1
]}

Das, Swagatam ^{[2
]}

机构：

[1] Indian Stat Inst, Kolkata, India

[2] Indian Stat Inst, Elect & Commun Sci Unit, Kolkata, India

来源：

STATISTICS & PROBABILITY LETTERS | 2020年 / 163卷

关键词：

Clustering; Hierarchical clustering; Optimal transport; Sinkhorn distance; MOLECULAR CLASSIFICATION; EFFICIENT ALGORITHM; PREDICTION; SELECTION;

D O I：

10.1016/j.spl.2020.108781

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Optimal Transport (OT) distances result in a powerful technique to compare the probability distributions. Defining a similarity measure between clusters has been an open problem in Statistics. This paper introduces a hierarchical clustering algorithm using the OT based distance measures and analyzes the performance of the proposed algorithm on standard datasets with respect to the existing and popular hierarchical clustering methods. (C) 2020 Elsevier B.V. All rights reserved.

引用

页数：7

共 36 条

[1]

Adler J., 2018, ADV NEURAL INFORM PR, P6754

[2]

Alcalá-Fdez J, 2011, J MULT-VALUED LOG S, V17, P255

[3]

Altschuler J., 2017, ADV NEURAL INFORM PR, P1964

[4]

[Anonymous], 2012, NUMERICAL ECOLOGY

[5]

[Anonymous], 2011, Modern hierarchical, agglomerative clustering algorithms

[6]

[Anonymous], 2009, ADV NEURAL INFORM PR

[7]

Arjovsky M, 2017, PR MACH LEARN RES, V70

[8]

Bazan E., 2018, FRENCH GERM DOCT WOR, P12

[9]

Blondel M., 2018, Proceedings of Machine Learning Research, P880

[10] Optimal Transport for Domain Adaptation [J].

Courty, Nicolas ;

Flamary, Remi ;

Tuia, Devis ;

Rakotomamonjy, Alain .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (09) :1853-1865

← 1 2 3 4 →