Litcius/Paper detail

Robust covariance estimation under $L_{4}-L_{2}$ norm equivalence

Shahar Mendelson, Nikita Zhivotovskiy

2020The Annals of Statistics31 citationsDOIOpen Access PDF

Abstract

Let $X$ be a centered random vector taking values in $\mathbb{R}^{d}$ and let $\Sigma=\mathbb{E}(X\otimes X)$ be its covariance matrix. We show that if $X$ satisfies an $L_{4}-L_{2}$ norm equivalence (sometimes referred to as the bounded kurtosis assumption), there is a covariance estimator $\hat{\Sigma}$ that exhibits almost the same performance one would expect had $X$ been a Gaussian vector. The procedure also improves the current state-of-the-art regarding high probability bounds in the sub-Gaussian case (sharp results were only known in expectation or with constant probability). In both scenarios the new bounds do not depend explicitly on the dimension $d$, but rather on the effective rank of the covariance matrix $\Sigma$.

Topics & Concepts

MathematicsCombinatoricsCovarianceKurtosisLaw of total covarianceCovariance matrixEstimatorMultivariate random variableEquivalence (formal languages)SigmaBounded functionEstimation of covariance matricesCovariance functionDimension (graph theory)GaussianApplied mathematicsDiscrete mathematicsStatisticsRandom variableMathematical analysisCovariance intersectionQuantum mechanicsPhysicsSparse and Compressive Sensing TechniquesStatistical Methods and InferenceTarget Tracking and Data Fusion in Sensor Networks
Robust covariance estimation under $L_{4}-L_{2}$ norm equivalence | Litcius