Bayesian inference for spectral projectors of the covariance matrix
dc.bibliographicCitation.firstPage | 1948 | eng |
dc.bibliographicCitation.issue | 1 | eng |
dc.bibliographicCitation.journalTitle | Electronic journal of statistics : EJS | eng |
dc.bibliographicCitation.lastPage | 1987 | eng |
dc.bibliographicCitation.volume | 12 | eng |
dc.contributor.author | Silin, Igor | |
dc.contributor.author | Spokoiny, Vladimir | |
dc.date.accessioned | 2022-06-21T12:23:24Z | |
dc.date.available | 2022-06-21T12:23:24Z | |
dc.date.issued | 2018 | |
dc.description.abstract | Let X1,…,Xn be an i.i.d. sample in Rp with zero mean and the covariance matrix Σ∗. The classical PCA approach recovers the projector P∗J onto the principal eigenspace of Σ∗ by its empirical counterpart ˆPJ. Recent paper [24] investigated the asymptotic distribution of the Frobenius distance between the projectors ∥ˆPJ−P∗J∥2, while [27] offered a bootstrap procedure to measure uncertainty in recovering this subspace P∗J even in a finite sample setup. The present paper considers this problem from a Bayesian perspective and suggests to use the credible sets of the pseudo-posterior distribution on the space of covariance matrices induced by the conjugated Inverse Wishart prior as sharp confidence sets. This yields a numerically efficient procedure. Moreover, we theoretically justify this method and derive finite sample bounds on the corresponding coverage probability. Contrary to [24, 27], the obtained results are valid for non-Gaussian data: the main assumption that we impose is the concentration of the sample covariance ˆΣ in a vicinity of Σ∗. Numerical simulations illustrate good performance of the proposed procedure even on non-Gaussian data in a rather challenging regime. | eng |
dc.description.version | publishedVersion | eng |
dc.identifier.uri | https://oa.tib.eu/renate/handle/123456789/9102 | |
dc.identifier.uri | https://doi.org/10.34657/8140 | |
dc.language.iso | eng | eng |
dc.publisher | Ithaca, NY : Cornell University Library | eng |
dc.relation.doi | https://doi.org/10.1214/18-EJS1451 | |
dc.relation.essn | 1935-7524 | |
dc.rights.license | CC BY 4.0 Unported | eng |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | eng |
dc.subject.ddc | 310 | eng |
dc.subject.other | Bernstein | eng |
dc.subject.other | Covariance matrix | eng |
dc.subject.other | Principal component analysis | eng |
dc.subject.other | Spectral projector | eng |
dc.subject.other | Von mises theorem | eng |
dc.title | Bayesian inference for spectral projectors of the covariance matrix | eng |
dc.type | Article | eng |
dc.type | Text | eng |
tib.accessRights | openAccess | eng |
wgl.contributor | WIAS | eng |
wgl.subject | Mathematik | eng |
wgl.type | Zeitschriftenartikel | eng |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Bayesian_inference_for_spectral_projectors.pdf
- Size:
- 622.99 KB
- Format:
- Adobe Portable Document Format
- Description: