Skip to Main content Skip to Navigation

Kernel methods for high dimensional data analysis

Alba Chiara de Vitis 1, 2
1 DATASHAPE - Understanding the Shape of Data
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
Abstract : Since data are being collected using an increasing number of features, datasets are of increasingly high dimension. Computational problems, related to the apparent dimension, i.e. the dimension of the vectors used to collect data, and theoretical problems, which depends notably on the effective dimension of the dataset, the so called intrinsic dimension, have affected high dimensional data analysis. In order to provide a suitable approach to data analysis in high dimensions, we introduce a more comprehensive scenario in the framework of metric measure spaces. The aim of this thesis, is to show how to take advantage of high dimensionality phenomena in the pure high dimensional regime. In particular, we aim at introducing a new point of view in the use of distances and probability measures defined on the data set. More specifically, we want to show that kernel methods, already used in the intrinsic low dimensional scenario in order to reduce dimensionality, can be investigated under purely high dimensional hypotheses, and further applied to cases not covered by the literature.
Complete list of metadatas

Cited literature [88 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Monday, March 2, 2020 - 2:23:07 PM
Last modification on : Monday, May 25, 2020 - 7:41:25 PM
Long-term archiving on: : Wednesday, June 3, 2020 - 2:12:24 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02419727, version 2


Alba Chiara de Vitis. Kernel methods for high dimensional data analysis. Computational Geometry [cs.CG]. Université Côte d'Azur, 2019. English. ⟨NNT : 2019AZUR4034⟩. ⟨tel-02419727v2⟩



Record views


Files downloads