FTRLProx_train_spMatrix: FTRL-Proximal Linear Model Fitting Function

In yanyachen/rFTRLProximal: FTRL-Proximal Algorithm

Description

FTRLProx_train_spMatrix estimates the weights of linear model using FTRL-Proximal Algorithm. This function is an C++ implementation. This function is used internally and is not intended for end-user direct usage.

Usage

FTRLProx_train_spMatrix(x, y, state, family, params, epoch, nthread, verbose)

Arguments

x	a transposed dgCMatrix.
y	a vector containing labels.
state	a previously built model state to continue the training from.
family	link function to be used in the model. "gaussian", "binomial" and "poisson" are avaliable.
params	a list of parameters of FTRL-Proximal Algorithm. alpha alpha in the per-coordinate learning rate beta beta in the per-coordinate learning rate l1 L1 regularization parameter l2 L2 regularization parameter dropout percentage of the input features to drop from each sample
epoch	The number of iterations over training data to train the model.
nthread	number of parallel threads used to run ftrl.
verbose	logical value. Indicating if the progress bar is displayed or not.

Value

a list of ftrl model state.

yanyachen/rFTRLProximal documentation built on May 4, 2019, 2:30 p.m.