A multidimensional data-driven sparse identification technique: the sparse proper generalized decomposition

View/Open
Document typeArticle
Defense date2018-01-01
Rights accessOpen Access
European Commission's projectAdMoRe - Empowered decision-making in simulation-based engineering: Advanced Model Reduction for real-time, inverse and optimization in industrial problems (EC-H2020-675919)
Abstract
Sparse model identification by means of data is especially cumbersome if the sought dynamics live in a high dimensional space. This usually involves the need for large amount of data, unfeasible in such a high dimensional settings. This well-known phenomenon, coined as the curse of dimensionality, is here overcome by means of the use of separate representations. We present a technique based on the same principles of the Proper Generalized Decomposition that enables the identification of complex laws in the low-data limit. We provide examples on the performance of the technique in up to ten dimensions.
CitationIbáñez, R., Abisset, E., Ammar, A., González, D., Cueto, E., Huerta, A., Duval, J., Chinesta Soria, F. A multidimensional data-driven sparse identification technique: the sparse proper generalized decomposition. "Complexity", 1 Gener 2018, vol. 2018, p. 1-11.
ISSN1076-2787
Publisher versionhttps://www.hindawi.com/journals/complexity/2018/5608286/
Files | Description | Size | Format | View |
---|---|---|---|---|
5608286 (1).pdf | 2,887Mb | View/Open |
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder