Distance Covariance Analysis

Benjamin Cowley, Joao Semedo, Amin Zandvakili, Matthew Smith, Adam Kohn, Byron Yu
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:242-251, 2017.

Abstract

We propose a dimensionality reduction method to identify linear projections that capture interactions between two or more sets of variables. The method, distance covariance analysis (DCA), can detect both linear and nonlinear relationships, and can take dependent variables into account. On previous testbeds and a new testbed that systematically assesses the ability to detect both linear and nonlinear interactions, DCA performs better than or comparable to existing methods, while being one of the fastest methods. To showcase the versatility of DCA, we also applied it to three different neurophysiological datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v54-cowley17a, title = {{Distance Covariance Analysis}}, author = {Cowley, Benjamin and Semedo, Joao and Zandvakili, Amin and Smith, Matthew and Kohn, Adam and Yu, Byron}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics}, pages = {242--251}, year = {2017}, editor = {Singh, Aarti and Zhu, Jerry}, volume = {54}, series = {Proceedings of Machine Learning Research}, month = {20--22 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v54/cowley17a/cowley17a.pdf}, url = {https://proceedings.mlr.press/v54/cowley17a.html}, abstract = {We propose a dimensionality reduction method to identify linear projections that capture interactions between two or more sets of variables. The method, distance covariance analysis (DCA), can detect both linear and nonlinear relationships, and can take dependent variables into account. On previous testbeds and a new testbed that systematically assesses the ability to detect both linear and nonlinear interactions, DCA performs better than or comparable to existing methods, while being one of the fastest methods. To showcase the versatility of DCA, we also applied it to three different neurophysiological datasets.} }
Endnote
%0 Conference Paper %T Distance Covariance Analysis %A Benjamin Cowley %A Joao Semedo %A Amin Zandvakili %A Matthew Smith %A Adam Kohn %A Byron Yu %B Proceedings of the 20th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2017 %E Aarti Singh %E Jerry Zhu %F pmlr-v54-cowley17a %I PMLR %P 242--251 %U https://proceedings.mlr.press/v54/cowley17a.html %V 54 %X We propose a dimensionality reduction method to identify linear projections that capture interactions between two or more sets of variables. The method, distance covariance analysis (DCA), can detect both linear and nonlinear relationships, and can take dependent variables into account. On previous testbeds and a new testbed that systematically assesses the ability to detect both linear and nonlinear interactions, DCA performs better than or comparable to existing methods, while being one of the fastest methods. To showcase the versatility of DCA, we also applied it to three different neurophysiological datasets.
APA
Cowley, B., Semedo, J., Zandvakili, A., Smith, M., Kohn, A. & Yu, B.. (2017). Distance Covariance Analysis. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 54:242-251 Available from https://proceedings.mlr.press/v54/cowley17a.html.

Related Material