Modeling and Stochastic Learning for Forecasting in High Dimensions by Anestis Antoniadis Jean-Michel Poggi & Xavier Brossat

Author:Anestis Antoniadis, Jean-Michel Poggi & Xavier Brossat
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

Step 1: Selection by thresholding

A first thresholding procedure allows to reduce the dimensionality of the problem

in a rather crude way by a simple inspection of the empirical correlations

between the signal and each element of the dictionary.

This first threshold is data driven and is chosen adaptively [15].

Step 2: OLS

Ordinary Least Square method is then used on the linear sub-model obtained

by considering the variables retained after the first step.

Step 3: Denoising by thresholding

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.