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.

References in corpus (6)

• Large sample theory of intrinsic and extrinsic sample means on manifolds--II
• Semi-parametric estimation of shifts
• A deconvolution approach to estimation of a common shape in a shifted curves model
• Efficient estimation for a subclass of shape invariant models
• Semiparametric curve alignment and shift density estimation for biological data
• Intrinsic Means on the Circle: Uniqueness, Locus and Asymptotics

Cited by in corpus (4)

• Modelling of functional profiles and explainable shape shifts detection: An approach combining the notion of the Fréchet mean with the shape invariant model
• How to compute the barycenter of a weighted graph
• Bayesian methods in the Shape Invariant Model (I): Posterior contraction rates on probability measures
• Bayesian methods in the Shape Invariant Model (II): Identifiability and posterior contraction rates on functional spaces