vix.ing · top · new · best · stats · spec

Exploring and measuring non-linear correlations: Copulas, Lightspeed\n Transportation and Clustering

2016/10/30 by Gautier Marti, Marti, Gautier, Sébastien Andler +5 · 1 citation
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Psychology · #Complex Systems and Time Series Analysis #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (stat.ML) #Mental Health Research Topics #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.1610.09659

openalex publication_date 2016/10/30 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

We propose a methodology to explore and measure the pairwise correlations\nthat exist between variables in a dataset. The methodology leverages copulas\nfor encoding dependence between two variables, state-of-the-art optimal\ntransport for providing a relevant geometry to the copulas, and clustering for\nsummarizing the main dependence patterns found between the variables. Some of\nthe clusters centers can be used to parameterize a novel dependence coefficient\nwhich can target or forget specific dependence patterns. Finally, we illustrate\nand benchmark the methodology on several datasets. Code and numerical\nexperiments are available online for reproducible research.\n

Cited by

Related