© Institute of Mathematical Statistics, 2004 LEAST ANGLE REGRESSION

By Bradley Efron, Trevor J. Hastie, Iain M. Johnstone, Robert Tibshirani

6,720 citations recorded by the source corpus.

The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to which the model will be applied. Typically we have available a large collection of possible covariates from which we hope to select a parsimonious set for the efficient prediction of a response variable. Least Angle Regression (LARS), a new model selection algorithm, is a useful and less greedy version of traditional forward selection methods. Three main properties are derived: (1) A simple modification of the LARS algorithm implements the Lasso, an attractive version of ordinary least squares that constrains the sum of the absolute regression coefficients; the LARS modification calculates all possible Lasso estimates for a given problem, using an order of magnitude less computer time than previous methods. (2) A different LARS modification efficiently implements Forward Stagewise linear regression, another promising new model selection method; this connection explains the similar numerical results previously observed for the Lasso and Stagewise, and helps us understand the properties of both methods, which are seen as constrained versions of the simpler LARS algorithm. (3) A simple approximation for the degrees of freedom of a LARS estimate is available, from which we derive a Cp estimate of prediction error; this allows a principled choice among the range of possible LARS estimates. LARS and its variants are computationally efficient: the paper describes a publicly available algorithm that requires only the same order of magnitude of computational effort as ordinary least squares applied to the full set of covariates.

Subfields: Control and Systems Engineering, Statistics and Probability, Optimization & Training, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

  1. Robert Tibshirani
  2. Francis R. Bach
  3. Sergey Levine
  4. Nicolai Meinshausen
  5. Peter Buhlmann
  6. Jan Peters
  7. Cun-Hui Zhang
  8. Pieter Abbeel

In Statistics and Probability

  1. Robert Tibshirani
  2. Martin J. Wainwright
  3. Peter Buhlmann
  4. Jianqing Fan
  5. Francis R. Bach
  6. Cun-Hui Zhang
  7. Sara A. van de Geer
  8. Nicolai Meinshausen

In Optimization & Training

  1. Francis R. Bach
  2. Peter Richtárik
  3. Martin Jaggi
  4. Simon Lacoste-Julien
  5. Julien Mairal
  6. Michael I. Jordan
  7. Nicolai Meinshausen
  8. Jason D. Lee

In Statistical Learning Theory

  1. Martin J. Wainwright
  2. Francis R. Bach
  3. Cun-Hui Zhang
  4. Nicolai Meinshausen
  5. Peter Buhlmann
  6. Robert Tibshirani
  7. Tong Zhang
  8. Sara A. van de Geer

Citations in the corpus