Big data: The curse of dimensionality in modeling

Er-wei Bai

doi:10.1109/ChiCC.2014.6896586

Back

Conference proceeding

Big data: The curse of dimensionality in modeling

Er-wei Bai

Proceedings of the 33rd Chinese Control Conference, pp.6-13

07/2014

DOI: 10.1109/ChiCC.2014.6896586

View Online

Abstract

The problem of variable selection in system identification of a high dimensional nonlinear non-parametric system is described. The inherent difficulty, the curse of dimensionality, is introduced. Its connections to various topics and research areas are briefly discussed including order determination, pattern recognition, data mining, machine learning, statistical regression and manifold embedding. Finally, two methods, top down and bottom up approaches are described in some details.

Approximation methods

Convergence

Correlation

Input variables

Manifolds

Noise

Optimization

Details

Title: Subtitle: Big data: The curse of dimensionality in modeling
Creators: Er-wei Bai - University of Iowa
Resource Type: Conference proceeding
Publication Details: Proceedings of the 33rd Chinese Control Conference, pp.6-13
Publisher: TCCT, CAA
DOI: 10.1109/ChiCC.2014.6896586
ISSN: 1934-1768
eISSN: 2161-2927
Language: English
Date published: 07/2014
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197269102771

Metrics

7 Record Views