The Experts below are selected from a list of 2115 Experts worldwide ranked by ideXlab platform
Nicolai Meinshausen - One of the best experts on this subject based on the ideXlab platform.
-
Right Singular Vector projection graphs fast high dimensional covariance matrix estimation under latent confounding
Journal of The Royal Statistical Society Series B-statistical Methodology, 2020Co-Authors: Rajen D Shah, Benjamin Frot, Gianandrea Thanei, Nicolai MeinshausenAbstract:We consider the problem of estimating a high dimensional p×p covariance matrix Σ, given n observations of confounded data with covariance Σ+ΓΓT, where Γ is an unknown p×q matrix of latent factor loadings. We propose a simple and scalable estimator based on the projection onto the Right Singular Vectors of the observed data matrix, which we call Right Singular Vector projection (RSVP). Our theoretical analysis of this method reveals that, in contrast with approaches based on the removal of principal components, RSVP can cope well with settings where the smallest eigenvalue of ΓTΓ is relatively close to the largest eigenvalue of Σ, as well as when the eigenvalues of ΓTΓ are diverging fast. RSVP does not require knowledge or estimation of the number of latent factors q, but it recovers Σ only up to an unknown positive scale factor. We argue that this suffices in many applications, e.g. if an estimate of the correlation matrix is desired. We also show that, by using subsampling, we can further improve the performance of the method. We demonstrate the favourable performance of RSVP through simulation experiments and an analysis of gene expression data sets collated by the GTEX consortium.
Rajen D Shah - One of the best experts on this subject based on the ideXlab platform.
-
Right Singular Vector projection graphs fast high dimensional covariance matrix estimation under latent confounding
Journal of The Royal Statistical Society Series B-statistical Methodology, 2020Co-Authors: Rajen D Shah, Benjamin Frot, Gianandrea Thanei, Nicolai MeinshausenAbstract:We consider the problem of estimating a high dimensional p×p covariance matrix Σ, given n observations of confounded data with covariance Σ+ΓΓT, where Γ is an unknown p×q matrix of latent factor loadings. We propose a simple and scalable estimator based on the projection onto the Right Singular Vectors of the observed data matrix, which we call Right Singular Vector projection (RSVP). Our theoretical analysis of this method reveals that, in contrast with approaches based on the removal of principal components, RSVP can cope well with settings where the smallest eigenvalue of ΓTΓ is relatively close to the largest eigenvalue of Σ, as well as when the eigenvalues of ΓTΓ are diverging fast. RSVP does not require knowledge or estimation of the number of latent factors q, but it recovers Σ only up to an unknown positive scale factor. We argue that this suffices in many applications, e.g. if an estimate of the correlation matrix is desired. We also show that, by using subsampling, we can further improve the performance of the method. We demonstrate the favourable performance of RSVP through simulation experiments and an analysis of gene expression data sets collated by the GTEX consortium.
Ovidio Mario Bucci - One of the best experts on this subject based on the ideXlab platform.
-
Blind Focusing of Electromagnetic Fields in Hyperthermia Exploiting Target Contrast Variations
IEEE Transactions on Biomedical Engineering, 2015Co-Authors: Gennaro Bellizzi, Ovidio Mario BucciAbstract:This paper suggests a novel approach to the blind focusing of the electromagnetic field for microwave hyperthermia. The idea is to induce a contrast variation in the target and to exploit this variation for the synthesis of the excitations of the antenna array employed for the focusing, by performing a differential scattering measurement. In particular, the excitation Vector is set as the Right Singular Vector associated with the largest Singular value of the differential scattering matrix, obtained as difference of two scattering matrixes measured by the antenna array itself before and after the contrast change. As a result, the approach is computationally effective and totally blind, not requiring any a priori knowledge of the electric and geometric features of the region hosting the target, as well as of its spatial position with respect to the antenna array.
-
Blind focusing in microwave hyperthermia by target contrast variation
The 8th European Conference on Antennas and Propagation (EuCAP 2014), 2014Co-Authors: Gennaro Bellizzi, Ovidio Mario BucciAbstract:The paper suggests a novel blind focusing approach for microwave hyperthermia. The idea is to exploit a contrast variation induced in the diseased tissue for the synthesis of the excitations of the antenna array employed for the field focusing, by performing a differential scattering measurement. In particular, the excitation Vector is set as the Right Singular Vector associated to the largest Singular value of the differential scattering data matrix, obtained as the difference of the scattering matrixes measured, by the antenna array itself, before and after the contrast change. The approach is computationally effective and totally blind, not requiring any a priori knowledge on the electric and geometric features of the region hosting the target and on its spatial location with respect to the antenna array.
Gianandrea Thanei - One of the best experts on this subject based on the ideXlab platform.
-
Right Singular Vector projection graphs: fast high dimensional covariance matrix estimation under latent confounding
'Organisation for Economic Co-Operation and Development (OECD)', 2020Co-Authors: Shah Rajen, Gianandrea Thanei, Frot B, Meinshausen NAbstract:In this work we consider the problem of estimating a high-dimensional $p \times p$ covariance matrix $\Sigma$, given $n$ observations of confounded data with covariance $\Sigma + \Gamma \Gamma^T$, where $\Gamma$ is an unknown $p \times q$ matrix of latent factor loadings. We propose a simple and scalable estimator based on the projection on to the Right Singular Vectors of the observed data matrix, which we call RSVP. Our theoretical analysis of this method reveals that in contrast to PCA-based approaches, RSVP is able to cope well with settings where the smallest eigenvalue of $\Gamma^T \Gamma$ is close to the largest eigenvalue of $\Sigma$, as well as settings where the eigenvalues of $\Gamma^T \Gamma$ are diverging fast. It is also able to handle data that may have heavy tails and only requires that the data has an elliptical distribution. RSVP does not require knowledge or estimation of the number of latent factors $q$, but only recovers $\Sigma$ up to an unknown positive scale factor. We argue this suffices in many applications, for example if an estimate of the correlation matrix is desired. We also show that by using subsampling, we can further improve the performance of the method. We demonstrate the favourable performance of RSVP through simulation experiments and an analysis of gene expression datasets collated by the GTEX consortium.Supported by an EPSRC First Grant and the Alan Turing Institute under the EPSRC grant EP/N510129/1
-
Right Singular Vector projection graphs fast high dimensional covariance matrix estimation under latent confounding
Journal of The Royal Statistical Society Series B-statistical Methodology, 2020Co-Authors: Rajen D Shah, Benjamin Frot, Gianandrea Thanei, Nicolai MeinshausenAbstract:We consider the problem of estimating a high dimensional p×p covariance matrix Σ, given n observations of confounded data with covariance Σ+ΓΓT, where Γ is an unknown p×q matrix of latent factor loadings. We propose a simple and scalable estimator based on the projection onto the Right Singular Vectors of the observed data matrix, which we call Right Singular Vector projection (RSVP). Our theoretical analysis of this method reveals that, in contrast with approaches based on the removal of principal components, RSVP can cope well with settings where the smallest eigenvalue of ΓTΓ is relatively close to the largest eigenvalue of Σ, as well as when the eigenvalues of ΓTΓ are diverging fast. RSVP does not require knowledge or estimation of the number of latent factors q, but it recovers Σ only up to an unknown positive scale factor. We argue that this suffices in many applications, e.g. if an estimate of the correlation matrix is desired. We also show that, by using subsampling, we can further improve the performance of the method. We demonstrate the favourable performance of RSVP through simulation experiments and an analysis of gene expression data sets collated by the GTEX consortium.
Benjamin Frot - One of the best experts on this subject based on the ideXlab platform.
-
Right Singular Vector projection graphs fast high dimensional covariance matrix estimation under latent confounding
Journal of The Royal Statistical Society Series B-statistical Methodology, 2020Co-Authors: Rajen D Shah, Benjamin Frot, Gianandrea Thanei, Nicolai MeinshausenAbstract:We consider the problem of estimating a high dimensional p×p covariance matrix Σ, given n observations of confounded data with covariance Σ+ΓΓT, where Γ is an unknown p×q matrix of latent factor loadings. We propose a simple and scalable estimator based on the projection onto the Right Singular Vectors of the observed data matrix, which we call Right Singular Vector projection (RSVP). Our theoretical analysis of this method reveals that, in contrast with approaches based on the removal of principal components, RSVP can cope well with settings where the smallest eigenvalue of ΓTΓ is relatively close to the largest eigenvalue of Σ, as well as when the eigenvalues of ΓTΓ are diverging fast. RSVP does not require knowledge or estimation of the number of latent factors q, but it recovers Σ only up to an unknown positive scale factor. We argue that this suffices in many applications, e.g. if an estimate of the correlation matrix is desired. We also show that, by using subsampling, we can further improve the performance of the method. We demonstrate the favourable performance of RSVP through simulation experiments and an analysis of gene expression data sets collated by the GTEX consortium.
