Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching

Mu Niu, Simon Rogers, Maurizio Filippone, Dirk Husmeier
; Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1699-1707, 2016.

Abstract

Parameter inference in mechanistic models of coupled differential equations is a topical and challenging problem. We propose a new method based on kernel ridge regression and gradient matching, and an objective function that simultaneously encourages goodness of fit and penalises inconsistencies with the differential equations. Fast minimisation is achieved by exploiting partial convexity inherent in this function, and setting up an iterative algorithm in the vein of the EM algorithm. An evaluation of the proposed method on various benchmark data suggests that it compares favourably with state-of-the-art alternatives.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-niu16, title = {Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching}, author = {Mu Niu and Simon Rogers and Maurizio Filippone and Dirk Husmeier}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {1699--1707}, year = {2016}, editor = {Maria Florina Balcan and Kilian Q. Weinberger}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/niu16.pdf}, url = {http://proceedings.mlr.press/v48/niu16.html}, abstract = {Parameter inference in mechanistic models of coupled differential equations is a topical and challenging problem. We propose a new method based on kernel ridge regression and gradient matching, and an objective function that simultaneously encourages goodness of fit and penalises inconsistencies with the differential equations. Fast minimisation is achieved by exploiting partial convexity inherent in this function, and setting up an iterative algorithm in the vein of the EM algorithm. An evaluation of the proposed method on various benchmark data suggests that it compares favourably with state-of-the-art alternatives.} }
Endnote
%0 Conference Paper %T Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching %A Mu Niu %A Simon Rogers %A Maurizio Filippone %A Dirk Husmeier %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-niu16 %I PMLR %J Proceedings of Machine Learning Research %P 1699--1707 %U http://proceedings.mlr.press %V 48 %W PMLR %X Parameter inference in mechanistic models of coupled differential equations is a topical and challenging problem. We propose a new method based on kernel ridge regression and gradient matching, and an objective function that simultaneously encourages goodness of fit and penalises inconsistencies with the differential equations. Fast minimisation is achieved by exploiting partial convexity inherent in this function, and setting up an iterative algorithm in the vein of the EM algorithm. An evaluation of the proposed method on various benchmark data suggests that it compares favourably with state-of-the-art alternatives.
RIS
TY - CPAPER TI - Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching AU - Mu Niu AU - Simon Rogers AU - Maurizio Filippone AU - Dirk Husmeier BT - Proceedings of The 33rd International Conference on Machine Learning PY - 2016/06/11 DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-niu16 PB - PMLR SP - 1699 DP - PMLR EP - 1707 L1 - http://proceedings.mlr.press/v48/niu16.pdf UR - http://proceedings.mlr.press/v48/niu16.html AB - Parameter inference in mechanistic models of coupled differential equations is a topical and challenging problem. We propose a new method based on kernel ridge regression and gradient matching, and an objective function that simultaneously encourages goodness of fit and penalises inconsistencies with the differential equations. Fast minimisation is achieved by exploiting partial convexity inherent in this function, and setting up an iterative algorithm in the vein of the EM algorithm. An evaluation of the proposed method on various benchmark data suggests that it compares favourably with state-of-the-art alternatives. ER -
APA
Niu, M., Rogers, S., Filippone, M. & Husmeier, D.. (2016). Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching. Proceedings of The 33rd International Conference on Machine Learning, in PMLR 48:1699-1707

Related Material