Skip to Main content Skip to Navigation
Journal articles

Minimax properties of Fréchet means of discretely sampled curves

Abstract : We study the problem of estimating a mean pattern from a set of similar curves in the setting where the variability in the data is due to random geometric deformations and additive noise. We propose an estimator based on the notion of Frechet mean that is a generalization of the standard notion of averaging to non-Euclidean spaces. We derive a minimax rate for this estimation problem, and we show that our estimator achieves this optimal rate under the asymptotics where both the number of curves and the number of sampling points go to infinity.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00737560
Contributor : Xavier Gendre <>
Submitted on : Tuesday, June 11, 2013 - 2:24:32 PM
Last modification on : Thursday, March 5, 2020 - 5:56:44 PM
Long-term archiving on: : Tuesday, April 4, 2017 - 7:25:08 PM

Files

aos1104.pdf
Files produced by the author(s)

Identifiers

Citation

Jérémie Bigot, Xavier Gendre. Minimax properties of Fréchet means of discretely sampled curves. Annals of Statistics, Institute of Mathematical Statistics, 2013, 41 (2), pp.923-956. ⟨10.1214/13-AOS1104⟩. ⟨hal-00737560v3⟩

Share

Metrics

Record views

333

Files downloads

429