Covariance Estimation From Compressive Data Partitions Using a Projected Gradient-Based Algorithm

@article{Monsalve2021CovarianceEF,
  title={Covariance Estimation From Compressive Data Partitions Using a Projected Gradient-Based Algorithm},
  author={Jonathan Monsalve and Juan Marcos Ram{\'i}rez and I{\~n}aki Esnaola and Henry Arguello},
  journal={IEEE Transactions on Image Processing},
  year={2021},
  volume={31},
  pages={4817-4827}
}
Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this… 

Compressive Covariance Sensing-Based Power Spectrum Estimation of Real-Valued Signals Subject to Sub-Nyquist Sampling

An estimate of the power spectrum of a real-valued wide-sense stationary autoregressive signal is computed from sub-Nyquist or compressed measurements in additive white Gaussian noise using the concepts of compressive covariance sensing and Blackman-Tukey nonparametric spectrum estimation.

Hierarchical Compressed Subspace Clustering Of Infrared Single-Pixel Measurements

This paper proposes a hierarchical approach to design the sensing matrix of the SPC, such that the pixel clustering task can be performed directly using the compressed infrared SPC measurements without a previous reconstruction step.

Cocosvi: Single Snapshot Compressive Spectral Video Via Covariance Matrix Estimation

A snapshot spectral video imager based on the compressive covariance sampling (CCS) theory, named CoCoS-Vi, and a low-rank optimization problem that exploits the covariance matrix (CM) spectrotemporal correlation to improve the reconstruction accuracy is proposed.

References

SHOWING 1-10 OF 51 REFERENCES

Estimation of the sample covariance matrix from compressive measurements

This paper presents an unbiased estimator to extract the covariance structure from compressive measurements obtained by a general class of random projection matrices consisting of i.i.d. zero-mean entries and finite first four moments and proposes an approach to covariance estimation that utilizes sparse Rademacher matrices.

Covalsa: Covariance estimation from compressive measurements using alternating minimization

A class of convex formulations and respective solutions to the high-dimensional covariance matrix estimation problem under compressive measurements, imposing either Toeplitz, sparseness, null-pattern, low rank, or low permuted rank structure on the solution, in addition to positive semi-definiteness.

Extreme Compressive Sampling for Covariance Estimation

An estimator based on back-projections of these compressive samples is proposed and analyzed, and lower bounds showing that this estimator is minimax-optimal for both infinity and spectral norm estimation problems are established.

Efficient recovery of principal components from compressive measurements with application to Gaussian mixture model estimation

It is shown that, as the number of data samples increases, the eigenvectors (principal components) of the empirical covariance matrix of a simple matrix-vector multiplication of the compressive measurements converge to the true principal components of the original data.

Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming

This paper explores a quadratic (or rank-one) measurement model which imposes minimal memory requirements and low computational complexity during the sampling process, and is shown to be optimal in preserving various low-dimensional covariance structures.

Compressive Estimation and Imaging Based on Autoregressive Models

A novel framework for compressive estimation of autoregressive (AR) process parameters based on ad-hoc sensing matrix construction is proposed and a compressive least square estimator for AR(p) parameters and a specific AR(1) compressive Bayesian estimator is introduced.

Compressive Covariance Sensing-Based Power Spectrum Estimation of Real-Valued Signals Subject to Sub-Nyquist Sampling

An estimate of the power spectrum of a real-valued wide-sense stationary autoregressive signal is computed from sub-Nyquist or compressed measurements in additive white Gaussian noise using the concepts of compressive covariance sensing and Blackman-Tukey nonparametric spectrum estimation.

Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data

This work rigorously proves that the proposed estimator is unbiased and requires smaller data to achieve the same accuracy with specially designed sampling distributions and implies an improved tradeoff between the estimation accuracy and computational costs.

Wideband Spectrum Sensing From Compressed Measurements Using Spectral Prior Information

This paper uses the asymptotic theory of circulant matrices to propose a dimensionality reduction technique that simplifies existing structured covariance estimation algorithms, achieving a similar performance at a much lower computational cost.

Compressive-Projection Principal Component Analysis

  • J. Fowler
  • Computer Science
    IEEE Transactions on Image Processing
  • 2009
CPPCA constitutes a fundamental departure from traditional PCA in that it permits its excellent dimensionality-reduction and compression performance to be realized in an light-encoder/heavy-decoder system architecture.
...