Home > Research > Publications & Outputs > CatReg: Solution Paths for Linear and Logistic ...

Links

View graph of relations

CatReg: Solution Paths for Linear and Logistic Regression Models with SCOPE Penalty

Research output: Exhibits, objects and web-based outputsSoftware

Published

Standard

CatReg: Solution Paths for Linear and Logistic Regression Models with SCOPE Penalty. Benjamin Stokell (Artist); Rajen Shah (Artist); Grose, Daniel (Developer). 2020.

Research output: Exhibits, objects and web-based outputsSoftware

Harvard

APA

Vancouver

Author

Bibtex

@misc{6def2fd2128d409b9299f6ea5db97f70,
title = "CatReg: Solution Paths for Linear and Logistic Regression Models with SCOPE Penalty",
abstract = "Computes solutions for linear and logistic regression models with a nonconvex penalty (SCOPE) in an efficient path-wise fashion (Stokell, Shah and Tibshirani 2020, ). The scaling of the solution paths is selected automatically. Includes functionality for selecting tuning parameter lambda by k-fold cross-validation and early termination based on information criteria. Solutions are computed by cyclical block-coordinate descent, iterating an innovative dynamic programming algorithm to compute exact solutions for each block.",
author = "{Benjamin Stokell} and {Rajen Shah} and Daniel Grose",
year = "2020",
month = mar,
day = "14",
language = "English",

}

RIS

TY - ADVS

T1 - CatReg: Solution Paths for Linear and Logistic Regression Models with SCOPE Penalty

A2 - Benjamin Stokell

A2 - Rajen Shah

A2 - Grose, Daniel

PY - 2020/3/14

Y1 - 2020/3/14

N2 - Computes solutions for linear and logistic regression models with a nonconvex penalty (SCOPE) in an efficient path-wise fashion (Stokell, Shah and Tibshirani 2020, ). The scaling of the solution paths is selected automatically. Includes functionality for selecting tuning parameter lambda by k-fold cross-validation and early termination based on information criteria. Solutions are computed by cyclical block-coordinate descent, iterating an innovative dynamic programming algorithm to compute exact solutions for each block.

AB - Computes solutions for linear and logistic regression models with a nonconvex penalty (SCOPE) in an efficient path-wise fashion (Stokell, Shah and Tibshirani 2020, ). The scaling of the solution paths is selected automatically. Includes functionality for selecting tuning parameter lambda by k-fold cross-validation and early termination based on information criteria. Solutions are computed by cyclical block-coordinate descent, iterating an innovative dynamic programming algorithm to compute exact solutions for each block.

M3 - Software

ER -