English

Optimal High-Dimensional Shrinkage Covariance Estimation for Elliptical Distributions

Methodology 2017-07-03 v1

Abstract

We derive an optimal shrinkage sample covariance matrix (SCM) estimator which is suitable for high dimensional problems and when sampling from an unspecified elliptically symmetric distribution. Specifically, we derive the optimal (oracle) shrinkage parameters that obtain the minimum mean-squared error (MMSE) between the shrinkage SCM and the true covariance matrix when sampling from an elliptical distribution. Subsequently, we show how the oracle shrinkage parameters can be consistently estimated under the random matrix theory regime. Simulations show the advantage of the proposed estimator over the conventional shrinkage SCM estimator due to Ledoit and Wolf (2004). The proposed shrinkage SCM estimator often provides significantly better performance than the Ledoit-Wolf estimator and has the advantage that consistency is guaranteed over the whole class of elliptical distributions with finite 4th order moments.

Keywords

Cite

@article{arxiv.1706.10066,
  title  = {Optimal High-Dimensional Shrinkage Covariance Estimation for Elliptical Distributions},
  author = {Esa Ollila},
  journal= {arXiv preprint arXiv:1706.10066},
  year   = {2017}
}

Comments

Accepted in the 25th European Signal Processing Conference (EUSIPCO 2017), published by EURASIP, scheduled for Aug. 28 - Sep. 2 in Kos island, Greece

R2 v1 2026-06-22T20:34:13.811Z