Stochastic development regression using method of moments

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

This paper considers the estimation problem arising when inferring parameters in the stochastic development regression model for manifold valued non-linear data. Stochastic development regression captures the relation between manifold-valued response and Euclidean covariate variables using the stochastic development construction. It is thereby able to incorporate several covariate variables and random effects. The model is intrinsically defined using the connection of the manifold, and the use of stochastic development avoids linearizing the geometry. We propose to infer parameters using the Method of Moments procedure that matches known constraints on moments of the observations conditional on the latent variables. The performance of the model is investigated in a simulation example using data on finite dimensional landmark manifolds.

OriginalsprogEngelsk
TitelGeometric Science of Information : Third International Conference, GSI 2017, Paris, France, November 7-9, 2017, Proceedings
RedaktørerFrank Nielsen, Fréderic Barbaresco
Antal sider9
ForlagSpringer
Publikationsdato2017
Sider3-11
ISBN (Trykt)978-3-319-68444-4
ISBN (Elektronisk)978-3-319-68445-1
DOI
StatusUdgivet - 2017
Begivenhed3rd International Conference on Geometric Science of Information - Paris, Frankrig
Varighed: 7 nov. 20179 nov. 2017
Konferencens nummer: 3

Konference

Konference3rd International Conference on Geometric Science of Information
Nummer3
LandFrankrig
ByParis
Periode07/11/201709/11/2017
NavnLecture notes in computer science
Vol/bind10589
ISSN0302-9743

ID: 188481061