Sharp Convergence Rates for Forward Regression in High-Dimensional Sparse Linear Models
Machine Learning
2018-04-12 v3
Abstract
Forward regression is a statistical model selection and estimation procedure which inductively selects covariates that add predictive power into a working statistical regression model. Once a model is selected, unknown regression parameters are estimated by least squares. This paper analyzes forward regression in high-dimensional sparse linear models. Probabilistic bounds for prediction error norm and number of selected covariates are proved. The analysis in this paper gives sharp rates and does not require beta-min or irrepresentability conditions.
Cite
@article{arxiv.1702.01000,
title = {Sharp Convergence Rates for Forward Regression in High-Dimensional Sparse Linear Models},
author = {Damian Kozbur},
journal= {arXiv preprint arXiv:1702.01000},
year = {2018}
}
Comments
arXiv admin note: text overlap with arXiv:1512.02666