Ecole d'ingénieur et centre de recherche en Sciences du numérique

Statistical inference in mechanistic models: time warping for improved gradient matching

Niu, Mu; Macdonald, Benn; Rogers, Simon; Filippone, Maurizio; Husmeier, Dirk

Computational Statistics, August 2017

Inference in mechanistic models of non-linear differential equations is a challenging problem in current computational statistics. Due to the high computational costs of numerically solving the differential equations in every step of an iterative parameter adaptation scheme, approximate methods based on gradient matching have become popular. However, these methods critically depend on the smoothing scheme for function interpolation. The present article adapts an idea from manifold learning and demonstrates that a time warping approach aiming to homogenize intrinsic length scales can lead to a significant improvement in parameter estimation accuracy. We demonstrate the effectiveness of this scheme on noisy data from two dynamical systems with periodic limit cycle, a biopathway, and an application from soft-tissue mechanics. Our study also provides a comparative evaluation on a wide range of signal-to-noise ratios.

Document Doi Bibtex

Titre:Statistical inference in mechanistic models: time warping for improved gradient matching
Type:Journal
Langue:English
Ville:
Date:
Département:Data Science
Eurecom ref:5281
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in Computational Statistics, August 2017 and is available at : http://dx.doi.org/10.1007/s00180-017-0753-z
Bibtex: @article{EURECOM+5281, doi = {http://dx.doi.org/10.1007/s00180-017-0753-z}, year = {2017}, month = {08}, title = {{S}tatistical inference in mechanistic models: time warping for improved gradient matching}, author = {{N}iu, {M}u and {M}acdonald, {B}enn and {R}ogers, {S}imon and {F}ilippone, {M}aurizio and {H}usmeier, {D}irk}, journal = {{C}omputational {S}tatistics, {A}ugust 2017}, url = {http://www.eurecom.fr/publication/5281} }
Voir aussi: