README.md

In anuf/lassoSparkR: Implements LASSO Algorithms for Estimation in Linear Models to be run in Apache Spark Engine

lassoSparkR

A R package that implements several algorithms of the LASSO method for estimation in linear models to be run in Apache Spark engine.

LASSO stands for 'Least Absolute Shrinkage ans Selection Operator'1.

Three implementations will be covered: Shooting algorithm2 Secuential Stochastic Coordinate Descent (SCD)3 * Parallel Stochastic Coordinate Descent (Shotgun)3

[1] Tibshirani, R., "Regression Shrinkage and Selection via the Lasso" [1996]

[2] Fu, W. J., "Penalized Regressions: The Bridge Versus the Lasso" [1998]

[3] Bradley, J. C., Kyrola, A., Bickson D., Guestrin, C., "Parallel Coordinate Descent for L1-Regularized Loss Minimization" [2011]

anuf/lassoSparkR documentation built on May 31, 2019, 8:04 a.m.