A0513
Title: A nonparametric method to detect the number of components for dimensionality reduction techniques
Authors: Enea Bongiorno - Universita del Piemonte Orientale (Italy) [presenting]
Kwo Lik Lax Chan - Universita degli Studi del Piemonte Orientale (Italy)
Aldo Goia - Universita' del Piemonte Orientale (Italy)
Philippe Vieu - University Paul Sabatier (France)
Abstract: Working with data in high-dimensional or infinite-dimensional spaces often necessitates the use of dimensionality reduction techniques. One of the primary challenges is determining the number of components (or dimensions) to consider. A nonparametric technique is proposed to address this issue based on the concepts of complexity and small-ball probability. The method is demonstrated through examples and practical applications.
