How Correlations Influence Lasso Prediction

Abstract : We study how correlations in the design matrix influence Lasso prediction. First, we argue that the higher the correlations are, the smaller the optimal tuning parameter is. This implies in particular that the standard tuning parameters, that do not depend on the design matrix, are not favorable. Furthermore, we argue that Lasso prediction works well for any degree of correlations if suitable tuning parameters are chosen. We study these two subjects theoretically as well as with simulations.
Document type :
Preprints, Working Papers, ...
2012


https://hal.archives-ouvertes.fr/hal-00686055
Contributor : Mohamed Hebiri <>
Submitted on : Friday, July 6, 2012 - 3:14:56 PM
Last modification on : Wednesday, April 1, 2015 - 1:00:22 AM
Document(s) archivé(s) le : Sunday, October 7, 2012 - 2:30:54 AM

Files

HebiriLederer12.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00686055, version 2
  • ARXIV : 1204.1605

Collections

Citation

Mohamed Hebiri, Johannes Lederer. How Correlations Influence Lasso Prediction. 2012. <hal-00686055v2>

Export

Share

Metrics

Record views

101

Document downloads

41