sag_fit: Stochastic Average Gradient

In IshmaelBelghazi/bigoptim: Efficient Large Scale Convex Finite Sums Optimization

Usage

sag_fit(X, y, lambda = 0, maxiter = NULL, w = NULL, alpha = NULL,
  stepSizeType = 1, Li = NULL, Lmax = NULL, increasing = TRUE,
  d = NULL, g = NULL, covered = NULL, standardize = FALSE,
  tol = 0.001, family = "binomial", fit_alg = "constant",
  monitor = FALSE, user_loss_function = NULL, ...)

Arguments

X	Matrix, possibly sparse of features.
y	Matrix of targets.
lambda	Scalar. L2 regularization parameter.
maxiter	Maximum number of iterations.
w	Matrix of weights.
alpha	constant step-size. Used only when fit_alg == "constant"
stepSizeType	scalar default is 1 to use 1/L, set to 2 to use 2/(L + n*myu). Only used when fit_alg="linesearch"
Li	Scalar or Matrix.Initial individual Lipschitz approximation.
Lmax	Initial global Lipschitz approximation.
increasing	Boolean. TRUE allows for both increase and decrease of lipschitz coefficients. False allows only decrease.
d	Initial approximation of cost function gradient.
g	Initial approximation of individual losses gradient.
covered	Matrix of covered samples.
standardize	Boolean. Scales the data if True
tol	Real. Miminal required approximate gradient norm before convergence.
family	One of "binomial", "gaussian", "exponential" or "poisson"
fit_alg	One of "constant", "linesearch" (default), or "adaptive"
monitor	Boolean. If TRUE returns matrix of weights after each effective pass through the dataset.
user_loss_function	User supplied R or C loss and gradient functions
...	Any other pass-through parameters.

Value

object of class SAG_fit

IshmaelBelghazi/bigoptim documentation built on May 7, 2019, 6:44 a.m.