Inverse finite-size scaling for high-dimensional significance analysis

Yingying Xu, Santeri Puranen, Jukka Corander, Yoshiyuki Kabashima

Research output: Contribution to journalArticleScientificpeer-review

7 Citations (Scopus)
212 Downloads (Pure)


We propose an efficient procedure for significance determination in high-dimensional dependence learning based on surrogate data testing, termed inverse finite-size scaling (IFSS). The IFSS method is based on our discovery of a universal scaling property of random matrices which enables inference about signal behavior from much smaller scale surrogate data than the dimensionality of the original data. As a motivating example, we demonstrate the procedure for ultra-high-dimensional Potts models with order of 1010 parameters. IFSS reduces the computational effort of the data-testing procedure by several orders of magnitude, making it very efficient for practical purposes. This approach thus holds considerable potential for generalization to other types of complex models.

Original languageEnglish
Article number062112
Pages (from-to)1-9
JournalPhysical Review E
Issue number6
Publication statusPublished - 6 Jun 2018
MoE publication typeA1 Journal article-refereed


Dive into the research topics of 'Inverse finite-size scaling for high-dimensional significance analysis'. Together they form a unique fingerprint.

Cite this