Effective Data-aware Covariance Estimator from Compressed Data

TL;DR

This paper introduces DACE, a data-aware weighted sampling method for unbiased covariance estimation from compressed high-dimensional data, improving accuracy and extending to multiclass classification with strong experimental validation.

Contribution

Proposes DACE, a novel data-aware weighted sampling estimator for unbiased covariance matrix estimation from compressed data, and extends it to multiclass classification with theoretical support.

Findings

DACE provides more accurate covariance estimates at the same compression ratio.

DACE achieves superior performance in multiclass classification tasks.

Extensive experiments validate the effectiveness of DACE on synthetic and real datasets.

Abstract

Estimating covariance matrix from massive high-dimensional and distributed data is significant for various real-world applications. In this paper, we propose a data-aware weighted sampling based covariance matrix estimator, namely DACE, which can provide an unbiased covariance matrix estimation and attain more accurate estimation under the same compression ratio. Moreover, we extend our proposed DACE to tackle multiclass classification problems with theoretical justification and conduct extensive experiments on both synthetic and real-world datasets to demonstrate the superior performance of our DACE.