Denoise a Covariance Matrix using Targeted shrinkage

 

This post will describe how to denoise a Covariance matrix using Targeted shrinkage. Constant Residual Eigen is the still the preferred method as Targeted shrinkage does slightly distort the Eigen Values representing signal

Practical use:
The Eigen Values are naturally stored in decreasing order. Once we find the range of Eigen Values that correspond to signal (using fit to Marcenko Pastur Distribution), we can then reset all other eigen values below this threshold to a constant value. This basically vaccums all the eigen values containing random noise into a single Eigen value. These transformed Eigen values are used with the original Eigen Vectors, to recreate a denoised covariance matrix, that will be used for further processing.

Compute using Python:

# File: Denoise-Targeted-Shrinkage.py



Comments

Popular posts from this blog

1.2 Structured Data: Information Driven Bars

2.2 Labeling: Triple barrier method

Denoise a Covariance Matrix using Constant Residual Eigen Value Method