Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEs

Daniel E. Ochoa, Jorge I. Poveda, Anantharam Subbaraman, Gerd S. Schmidt, Farshad R. Pour-Safaei
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:866-878, 2021.

Abstract

We introduce a novel class of data-driven accelerated concurrent learning algorithms. Thesealgorithms are suitable for the solution of high-performance system identification and pa-rameter estimation problems withconvergence certificates, in settings where the standardpersistence of excitation (PE) condition is difficult to verifya priori. In order to achieve(uniform) fast convergence, the proposed algorithms exploit the existence of information-rich data sets, as well as certain non-smooth regularizations that generate a family ofnon-Lipschitz dynamics modeled as data-driven ordinary differential equations (DD-ODEs)and/or data-driven hybrid dynamical systems (DD-HDS). In each case, we provide stabilityand convergence certificates via Lyapunov theory. Moreover, to illustrate the advantages ofthe proposed algorithms, we consider an online estimation problem in Lithium-Ion batterieswhere the satisfaction of the PE condition is difficult to verify.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-ochoa21a, title = {Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth {ODE}s}, author = {Ochoa, Daniel E. and Poveda, Jorge I. and Subbaraman, Anantharam and Schmidt, Gerd S. and Pour-Safaei, Farshad R.}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {866--878}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/ochoa21a/ochoa21a.pdf}, url = {https://proceedings.mlr.press/v144/ochoa21a.html}, abstract = {We introduce a novel class of data-driven accelerated concurrent learning algorithms. Thesealgorithms are suitable for the solution of high-performance system identification and pa-rameter estimation problems withconvergence certificates, in settings where the standardpersistence of excitation (PE) condition is difficult to verifya priori. In order to achieve(uniform) fast convergence, the proposed algorithms exploit the existence of information-rich data sets, as well as certain non-smooth regularizations that generate a family ofnon-Lipschitz dynamics modeled as data-driven ordinary differential equations (DD-ODEs)and/or data-driven hybrid dynamical systems (DD-HDS). In each case, we provide stabilityand convergence certificates via Lyapunov theory. Moreover, to illustrate the advantages ofthe proposed algorithms, we consider an online estimation problem in Lithium-Ion batterieswhere the satisfaction of the PE condition is difficult to verify.} }
Endnote
%0 Conference Paper %T Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEs %A Daniel E. Ochoa %A Jorge I. Poveda %A Anantharam Subbaraman %A Gerd S. Schmidt %A Farshad R. Pour-Safaei %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-ochoa21a %I PMLR %P 866--878 %U https://proceedings.mlr.press/v144/ochoa21a.html %V 144 %X We introduce a novel class of data-driven accelerated concurrent learning algorithms. Thesealgorithms are suitable for the solution of high-performance system identification and pa-rameter estimation problems withconvergence certificates, in settings where the standardpersistence of excitation (PE) condition is difficult to verifya priori. In order to achieve(uniform) fast convergence, the proposed algorithms exploit the existence of information-rich data sets, as well as certain non-smooth regularizations that generate a family ofnon-Lipschitz dynamics modeled as data-driven ordinary differential equations (DD-ODEs)and/or data-driven hybrid dynamical systems (DD-HDS). In each case, we provide stabilityand convergence certificates via Lyapunov theory. Moreover, to illustrate the advantages ofthe proposed algorithms, we consider an online estimation problem in Lithium-Ion batterieswhere the satisfaction of the PE condition is difficult to verify.
APA
Ochoa, D.E., Poveda, J.I., Subbaraman, A., Schmidt, G.S. & Pour-Safaei, F.R.. (2021). Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEs. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:866-878 Available from https://proceedings.mlr.press/v144/ochoa21a.html.

Related Material