2016
DOI: 10.48550/arxiv.1609.00834
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Functional Data Analysis by Matrix Completion

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 0 publications
0
3
0
Order By: Relevance
“…When analysing functional data, one seldom has access to the genuinely infinite-dimensional objects (see, e.g., Hsing and Eubank [29], Yao et al [57,58], Descary and Panaretos [16]). In practice, the observed curves are discretised at some level and the data at hand represent finite-dimensional approximations, potentially featuring some additional level of smoothing.…”
Section: Stability Of Fréchet Meansmentioning
confidence: 99%
“…When analysing functional data, one seldom has access to the genuinely infinite-dimensional objects (see, e.g., Hsing and Eubank [29], Yao et al [57,58], Descary and Panaretos [16]). In practice, the observed curves are discretised at some level and the data at hand represent finite-dimensional approximations, potentially featuring some additional level of smoothing.…”
Section: Stability Of Fréchet Meansmentioning
confidence: 99%
“…Estimation of the covariance structure of processes is central to the estimation of individual trajectories. Descary and Panaretos (2016) propose a method where the estimate of the covariance matrix is obtained through matrix completion.…”
Section: Low-rank Approximationsmentioning
confidence: 99%
“…It is assumed that the measurement error process is at a much finer scale than the true covariate. This is achieved by imposing the following two conditions: 1) there exists δ > 0, such that cov(U (t), U (s)) = 0 if |s − t| > δ and 2) the covariance operator of X(•) is analytic on an open set containing |s − t| ≤ δ. Estimation of the covariance function of the error process under these conditions, is given in Descary & Panaretos (2016). The assumptions are more general than those made previously but still quite restrictive.…”
Section: Introductionmentioning
confidence: 99%