System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
2014 (English)In: IEEE Transactions on Automatic Control, ISSN 0018-9286, E-ISSN 1558-2523, Vol. 59, no 11, 2933-2945 p.Article in journal (Refereed) Published
Model estimation and structure detection with short data records are two issues that receive increasing interests in System Identification. In this paper, a multiple kernel-based regularization method is proposed to handle those issues. Multiple kernels are conic combinations of fixed kernels suitable for impulse response estimation, and equip the kernel-based regularization method with three features. First, multiple kernels can better capture complicated dynamics than single kernels. Second, the estimation of their weights by maximizing the marginal likelihood favors sparse optimal weights, which enables this method to tackle various structure detection problems, e. g., the sparse dynamic network identification and the segmentation of linear systems. Third, the marginal likelihood maximization problem is a difference of convex programming problem. It is thus possible to find a locally optimal solution efficiently by using a majorization minimization algorithm and an interior point method where the cost of a single interior-point iteration grows linearly in the number of fixed kernels. Monte Carlo simulations show that the locally optimal solutions lead to good performance for randomly generated starting points.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2014. Vol. 59, no 11, 2933-2945 p.
System identification; regularization; kernel; convex optimization; sparsity; structure detection
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:liu:diva-112818DOI: 10.1109/TAC.2014.2351851ISI: 000344482500007OAI: oai:DiVA.org:liu-112818DiVA: diva2:777075
Funding Agencies|Linnaeus Center CADICS - Swedish Research Council; ERC advanced grant LEARN ; ERC - European Research Council ; MIUR FIRB project "Learning meets time" [RBFR12M3AC]; European Community 2015-01-082014-12-172016-01-11