Sparse Functional Data Analysis Methods

Description

Provides algorithms to fit linear regression models under several popular penalization techniques and functional linear regression models based on Majorizing-Minimizing (MM) and Alternating Direction Method of Multipliers (ADMM) techniques. See Boyd et al (2010) <doi:10.1561/2200000016> for complete introduction to the method.

Package Content

Index of help topics:

confband                Function to plot the confidence bands
f2fSP                   Overlap Group Least Absolute Shrinkage and
                        Selection Operator for function-on-function
                        regression model
f2fSP_cv                Cross-validation for Overlap Group Least
                        Absolute Shrinkage and Selection Operator for
                        function-on-function regression model
f2sSP                   Overlap Group Least Absolute Shrinkage and
                        Selection Operator for scalar-on-function
                        regression model
f2sSP_cv                Cross-validation for Overlap Group Least
                        Absolute Shrinkage and Selection Operator on
                        scalar-on-function regression model
fdaSP-package           Sparse Functional Data Analysis Methods
lmSP                    Sparse Adaptive Overlap Group Least Absolute
                        Shrinkage and Selection Operator
lmSP_cv                 Cross-validation for Sparse Adaptive Overlap
                        Group Least Absolute Shrinkage and Selection
                        Operator
softhresh               Function to solve the soft thresholding problem

Maintainer

Mauro Bernardi <mauro.bernardi@unipd.it>

Author(s)

Mauro Bernardi [aut, cre], Marco Stefanucci [aut], Antonio Canale [ctb]

Function to plot the confidence bands

Description

Function to plot the confidence bands

Usage

confband(xV, yVmin, yVmax)

Arguments

Value

a polygon.

Overlap Group Least Absolute Shrinkage and Selection Operator for function-on-function regression model

Description

Overlap Group-LASSO for function-on-function regression model solves the following optimization problem

\textrm{min}_{\psi} ~ \frac{1}{2} \sum_{i=1}^n \int \left( y_i(s) - \int x_i(t) \psi(t,s) dt \right)^2 ds + \lambda \sum_{g=1}^{G} \Vert S_{g}T\psi \Vert_2

to obtain a sparse coefficient vector \psi=\mathsf{vec}(\Psi)\in\mathbb{R}^{ML} for the functional penalized predictor x(t), where the coefficient matrix \Psi\in\mathbb{R}^{M\times L}, the regression function \psi(t,s)=\varphi(t)^\intercal\Psi\theta(s), \varphi(t) and \theta(s) are two B-splines bases of order d and dimension M and L, respectively. For each group g, each row of the matrix S_g\in\mathbb{R}^{d\times ML} has non-zero entries only for those bases belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each basis function belongs to more than one group. The diagonal matrix T\in\mathbb{R}^{ML\times ML} contains the basis-specific weights. These values are provided by the argument var_weights (see below). The regularization path is computed for the overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method.

Usage

f2fSP(
  mY,
  mX,
  L,
  M,
  group_weights = NULL,
  var_weights = NULL,
  standardize.data = TRUE,
  splOrd = 4,
  lambda = NULL,
  lambda.min.ratio = NULL,
  nlambda = 30,
  overall.group = FALSE,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

an (M\times L) solution matrix for the parameters \Psi, which corresponds to the minimum in-sample MSE.

sp.coef.path

an (n_\lambda\times M \times L) array of estimated \Psi coefficients for each lambda.

sp.fun

an (r_x\times r_y) matrix providing the estimated functional coefficient for \psi(t,s).

sp.fun.path

an (n_\lambda\times r_x\times r_y) array providing the estimated functional coefficients for \psi(t,s) for each lambda.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the minimum in-sample MSE.

mse

in-sample mean squared error.

min.mse

minimum value of the in-sample MSE for the sequence of lambda.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

When you run the algorithm, output returns not only the solution, but also the iteration history recording following fields over iterates,

objval

objective function value.

r_norm

norm of primal residual.

s_norm

norm of dual residual.

eps_pri

feasibility tolerance for primal feasibility condition.

eps_dual

feasibility tolerance for dual feasibility condition.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) and Lin et al. (2022) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) and Lin et al. (2022) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Examples

## generate sample data
set.seed(4321)
s  <- seq(0, 1, length.out = 100)
t  <- seq(0, 1, length.out = 100)
p1 <- 5
p2 <- 6
r  <- 10
n  <- 50

beta_basis1 <- splines::bs(s, df = p1, intercept = TRUE)    # first basis for beta
beta_basis2 <- splines::bs(s, df = p2, intercept = TRUE)    # second basis for beta

data_basis <- splines::bs(s, df = r, intercept = TRUE)    # basis for X

x_0   <- apply(matrix(rnorm(p1 * p2, sd = 1), p1, p2), 1, 
               fdaSP::softhresh, 1.5)  # regression coefficients 
x_fun <- beta_basis2 %*% x_0 %*%  t(beta_basis1)  

fun_data <- matrix(rnorm(n*r), n, r) %*% t(data_basis)
b        <- fun_data %*% x_fun + rnorm(n * 100, sd = sd(fun_data %*% x_fun )/3)

## set the hyper-parameters
maxit          <- 1000
rho_adaptation <- FALSE
rho            <- 1
reltol         <- 1e-5
abstol         <- 1e-5

## fit functional regression model
mod <- f2fSP(mY = b, mX = fun_data, L = p1, M = p2,
             group_weights = NULL, var_weights = NULL, standardize.data = FALSE, splOrd = 4,
             lambda = NULL, nlambda = 30, lambda.min.ratio = NULL, 
             control = list("abstol" = abstol, 
                            "reltol" = reltol, 
                            "maxit" = maxit, 
                            "adaptation" = rho_adaptation, 
                            rho = rho, 
             "print.out" = FALSE))
 
mycol <- function (n) {
palette <- colorRampPalette(RColorBrewer::brewer.pal(11, "Spectral"))
palette(n)
}
cols <- mycol(1000)

oldpar <- par(mfrow = c(1, 2))
image(x_0, col = cols)
image(mod$sp.coefficients, col = cols)
par(oldpar)

oldpar <- par(mfrow = c(1, 2))
image(x_fun, col = cols)
contour(x_fun, add = TRUE)
image(beta_basis2 %*% mod$sp.coefficients %*% t(beta_basis1), col = cols)
contour(beta_basis2 %*% mod$sp.coefficients %*% t(beta_basis1), add = TRUE)
par(oldpar)

Cross-validation for Overlap Group Least Absolute Shrinkage and Selection Operator for function-on-function regression model

Description

Overlap Group-LASSO for function-on-function regression model solves the following optimization problem

\textrm{min}_{\psi} ~ \frac{1}{2} \sum_{i=1}^n \int \left( y_i(s) - \int x_i(t) \psi(t,s) dt \right)^2 ds + \lambda \sum_{g=1}^{G} \Vert S_{g}T\psi \Vert_2

to obtain a sparse coefficient vector \psi=\mathsf{vec}(\Psi)\in\mathbb{R}^{ML} for the functional penalized predictor x(t), where the coefficient matrix \Psi\in\mathbb{R}^{M\times L}, the regression function \psi(t,s)=\varphi(t)^\intercal\Psi\theta(s), \varphi(t) and \theta(s) are two B-splines bases of order d and dimension M and L, respectively. For each group g, each row of the matrix S_g\in\mathbb{R}^{d\times ML} has non-zero entries only for those bases belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each basis function belongs to more than one group. The diagonal matrix T\in\mathbb{R}^{ML\times ML} contains the basis-specific weights. These values are provided by the argument var_weights (see below). The regularization path is computed for the overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method.

Usage

f2fSP_cv(
  mY,
  mX,
  L,
  M,
  group_weights = NULL,
  var_weights = NULL,
  standardize.data = FALSE,
  splOrd = 4,
  lambda = NULL,
  lambda.min.ratio = NULL,
  nlambda = NULL,
  cv.fold = 5,
  overall.group = FALSE,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

an (M\times L) solution matrix for the parameters \Psi, which corresponds to the minimum cross-validated MSE.

sp.fun

an (r_x\times r_y) matrix providing the estimated functional coefficient for \psi(t,s) corresponding to the minimum cross-validated MSE.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the cross-validated minimum mean squared error.

indi.min.mse

index of the lambda sequence corresponding to lambda.min.

mse

cross-validated mean squared error.

min.mse

minimum value of the cross-validated MSE for the sequence of lambda.

mse.sd

standard deviation of the cross-validated mean squared error.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) and Lin et al. (2022) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) and Lin et al. (2022) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Examples

## generate sample data
set.seed(4321)
s  <- seq(0, 1, length.out = 100)
t  <- seq(0, 1, length.out = 100)
p1 <- 5
p2 <- 6
r  <- 10
n  <- 50

beta_basis1 <- splines::bs(s, df = p1, intercept = TRUE)    # first basis for beta
beta_basis2 <- splines::bs(s, df = p2, intercept = TRUE)    # second basis for beta

data_basis <- splines::bs(s, df = r, intercept = TRUE)    # basis for X

x_0   <- apply(matrix(rnorm(p1 * p2, sd = 1), p1, p2), 1, 
               fdaSP::softhresh, 1.5)  # regression coefficients 
x_fun <- beta_basis2 %*% x_0 %*%  t(beta_basis1)  

fun_data <- matrix(rnorm(n*r), n, r) %*% t(data_basis)
b        <- fun_data %*% x_fun + rnorm(n * 100, sd = sd(fun_data %*% x_fun )/3)

## set the hyper-parameters
maxit          <- 1000
rho_adaptation <- FALSE
rho            <- 0.01
reltol         <- 1e-5
abstol         <- 1e-5

## fit functional regression model
mod_cv <- f2fSP_cv(mY = b, mX = fun_data, L = p1, M = p2,
                   group_weights = NULL, var_weights = NULL, 
                   standardize.data = FALSE, splOrd = 4,
                   lambda = NULL, nlambda = 30, cv.fold = 5, 
                   lambda.min.ratio = NULL,
                   control = list("abstol" = abstol, 
                                  "reltol" = reltol, 
                                  "maxit" = maxit, 
                                  "adaptation" = rho_adaptation, 
                                  "rho" = rho, 
                                  "print.out" = FALSE))

### graphical presentation
plot(log(mod_cv$lambda), mod_cv$mse, type = "l", col = "blue", lwd = 2, bty = "n", 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "Prediction Error", 
     ylim = range(mod_cv$mse - mod_cv$mse.sd, mod_cv$mse + mod_cv$mse.sd),
     main = "Cross-validated Prediction Error")
fdaSP::confband(xV = log(mod_cv$lambda), yVmin = mod_cv$mse - mod_cv$mse.sd, 
                yVmax = mod_cv$mse + mod_cv$mse.sd)       
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), col = "red", lwd = 1.0)

### comparison with oracle error
mod <- f2fSP(mY = b, mX = fun_data, L = p1, M = p2,
             group_weights = NULL, var_weights = NULL, 
             standardize.data = FALSE, splOrd = 4,
             lambda = NULL, nlambda = 30, lambda.min.ratio = NULL, 
             control = list("abstol" = abstol, 
                            "reltol" = reltol, 
                            "maxit" = maxit,
                            "adaptation" = rho_adaptation, 
                            "rho" = rho, 
                            "print.out" = FALSE))
err_mod <- apply(mod$sp.coef.path, 1, function(x) sum((x - x_0)^2))
plot(log(mod$lambda), err_mod, type = "l", col = "blue", lwd = 2, 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), 
     ylab = "Estimation Error", main = "True Estimation Error", bty = "n")
abline(v = log(mod$lambda[which(err_mod == min(err_mod))]), col = "red", lwd = 1.0)
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0, lty = 2)

Overlap Group Least Absolute Shrinkage and Selection Operator for scalar-on-function regression model

Description

Overlap Group-LASSO for scalar-on-function regression model solves the following optimization problem

\textrm{min}_{\psi,\gamma} ~ \frac{1}{2} \sum_{i=1}^n \left( y_i - \int x_i(t) \psi(t) dt-z_i^\intercal\gamma \right)^2 + \lambda \sum_{g=1}^{G} \Vert S_{g}T\psi \Vert_2

to obtain a sparse coefficient vector \psi\in\mathbb{R}^{M} for the functional penalized predictor x(t) and a coefficient vector \gamma\in\mathbb{R}^q for the unpenalized scalar predictors z_1,\dots,z_q. The regression function is \psi(t)=\varphi(t)^\intercal\psi where \varphi(t) is a B-spline basis of order d and dimension M. For each group g, each row of the matrix S_g\in\mathbb{R}^{d\times M} has non-zero entries only for those bases belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each basis function belongs to more than one group. The diagonal matrix T\in\mathbb{R}^{M\times M} contains the basis-specific weights. These values are provided by the argument var_weights (see below). The regularization path is computed for the overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method.

Usage

f2sSP(
  vY,
  mX,
  mZ = NULL,
  M,
  group_weights = NULL,
  var_weights = NULL,
  standardize.data = TRUE,
  splOrd = 4,
  lambda = NULL,
  nlambda = 30,
  lambda.min.ratio = NULL,
  intercept = FALSE,
  overall.group = FALSE,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

a length-M solution vector for the parameters \psi, which corresponds to the minimum in-sample MSE.

sp.coef.path

an (n_\lambda\times M) matrix of estimated \psi coefficients for each lambda.

sp.fun

a length-r vector providing the estimated functional coefficient for \psi(t).

sp.fun.path

an (n_\lambda\times r) matrix providing the estimated functional coefficients for \psi(t) for each lambda.

coefficients

a length-q solution vector for the parameters \gamma, which corresponds to the minimum in-sample MSE. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

coef.path

an (n_\lambda\times q) matrix of estimated \gamma coefficients for each lambda. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the minimum in-sample MSE.

mse

in-sample mean squared error.

min.mse

minimum value of the in-sample MSE for the sequence of lambda.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

When you run the algorithm, output returns not only the solution, but also the iteration history recording following fields over iterates,

objval

objective function value.

r_norm

norm of primal residual.

s_norm

norm of dual residual.

eps_pri

feasibility tolerance for primal feasibility condition.

eps_dual

feasibility tolerance for dual feasibility condition.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) and Lin et al. (2022) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) and Lin et al. (2022) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Examples

## generate sample data
set.seed(1)
n     <- 40
p     <- 18                                  # number of basis to GENERATE beta
r     <- 100
s     <- seq(0, 1, length.out = r)

beta_basis <- splines::bs(s, df = p, intercept = TRUE)    # basis
coef_data  <- matrix(rnorm(n*floor(p/2)), n, floor(p/2))        
fun_data   <- coef_data %*% t(splines::bs(s, df = floor(p/2), intercept = TRUE))     

x_0   <- apply(matrix(rnorm(p, sd=1),p,1), 1, fdaSP::softhresh, 1)  # regression coefficients 
x_fun <- beta_basis %*% x_0                

b     <- fun_data %*% x_fun + rnorm(n, sd = sqrt(crossprod(fun_data %*% x_fun ))/10)
l     <- 10^seq(2, -4, length.out = 30)
maxit <- 1000


## set the hyper-parameters
maxit          <- 1000
rho_adaptation <- TRUE
rho            <- 1
reltol         <- 1e-5
abstol         <- 1e-5

mod <- f2sSP(vY = b, mX = fun_data, M = p,
             group_weights = NULL, var_weights = NULL, standardize.data = FALSE, splOrd = 4,
             lambda = NULL, nlambda = 30, lambda.min = NULL, overall.group = FALSE, 
             control = list("abstol" = abstol, 
                            "reltol" = reltol, 
                            "adaptation" = rho_adaptation, 
                            "rho" = rho, 
                            "print.out" = FALSE)) 

# plot coefficiente path
matplot(log(mod$lambda), mod$sp.coef.path, type = "l", 
        xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "", bty = "n", lwd = 1.2)

Cross-validation for Overlap Group Least Absolute Shrinkage and Selection Operator on scalar-on-function regression model

Description

Overlap Group-LASSO for scalar-on-function regression model solves the following optimization problem

\textrm{min}_{\psi,\gamma} ~ \frac{1}{2} \sum_{i=1}^n \left( y_i - \int x_i(t) \psi(t) dt-z_i^\intercal\gamma \right)^2 + \lambda \sum_{g=1}^{G} \Vert S_{g}T\psi \Vert_2

to obtain a sparse coefficient vector \psi\in\mathbb{R}^{M} for the functional penalized predictor x(t) and a coefficient vector \gamma\in\mathbb{R}^q for the unpenalized scalar predictors z_1,\dots,z_q. The regression function is \psi(t)=\varphi(t)^\intercal\psi where \varphi(t) is a B-spline basis of order d and dimension M. For each group g, each row of the matrix S_g\in\mathbb{R}^{d\times M} has non-zero entries only for those bases belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each basis function belongs to more than one group. The diagonal matrix T\in\mathbb{R}^{M\times M} contains the basis specific weights. These values are provided by the argument var_weights (see below). The regularization path is computed for the overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method.

Usage

f2sSP_cv(
  vY,
  mX,
  mZ = NULL,
  M,
  group_weights = NULL,
  var_weights = NULL,
  standardize.data = FALSE,
  splOrd = 4,
  lambda = NULL,
  lambda.min.ratio = NULL,
  nlambda = NULL,
  cv.fold = 5,
  intercept = FALSE,
  overall.group = FALSE,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

a length-M solution vector solution vector for the parameters \psi, which corresponds to the minimum cross-validated MSE.

sp.fun

a length-r vector providing the estimated functional coefficient for \psi(t) corresponding to the minimum cross-validated MSE.

coefficients

a length-q solution vector for the parameters \gamma, which corresponds to the minimum cross-validated MSE. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the minimum cross-validated MSE.

mse

cross-validated mean squared error.

min.mse

minimum value of the cross-validated MSE for the sequence of lambda.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) and Lin et al. (2022) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) and Lin et al. (2022) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Examples

## generate sample data and functional coefficients
set.seed(1)
n     <- 40
p     <- 18                                 
r     <- 100
s     <- seq(0, 1, length.out = r)

beta_basis <- splines::bs(s, df = p, intercept = TRUE)    # basis
coef_data  <- matrix(rnorm(n*floor(p/2)), n, floor(p/2))        
fun_data   <- coef_data %*% t(splines::bs(s, df = floor(p/2), intercept = TRUE))     

x_0   <- apply(matrix(rnorm(p, sd=1),p,1), 1, fdaSP::softhresh, 1)  
x_fun <- beta_basis %*% x_0                

b     <- fun_data %*% x_fun + rnorm(n, sd = sqrt(crossprod(fun_data %*% x_fun ))/10)
l     <- 10^seq(2, -4, length.out = 30)
maxit <- 1000


## set the hyper-parameters
maxit          <- 1000
rho_adaptation <- TRUE
rho            <- 1
reltol         <- 1e-5
abstol         <- 1e-5

## run cross-validation
mod_cv <- f2sSP_cv(vY = b, mX = fun_data, M = p,
                   group_weights = NULL, var_weights = NULL, standardize.data = FALSE, splOrd = 4,
                   lambda = NULL, lambda.min = 1e-5, nlambda = 30, cv.fold = 5, intercept = FALSE, 
                   control = list("abstol" = abstol, 
                                  "reltol" = reltol, 
                                  "adaptation" = rho_adaptation,
                                  "rho" = rho, 
                                  "print.out" = FALSE))
                                          
### graphical presentation
plot(log(mod_cv$lambda), mod_cv$mse, type = "l", col = "blue", lwd = 2, bty = "n", 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "Prediction Error", 
     ylim = range(mod_cv$mse - mod_cv$mse.sd, mod_cv$mse + mod_cv$mse.sd),
     main = "Cross-validated Prediction Error")
fdaSP::confband(xV = log(mod_cv$lambda), yVmin = mod_cv$mse - mod_cv$mse.sd, 
                yVmax = mod_cv$mse + mod_cv$mse.sd)       
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0)

### comparison with oracle error
mod <- f2sSP(vY = b, mX = fun_data, M = p, 
             group_weights = NULL, var_weights = NULL, 
             standardize.data = FALSE, splOrd = 4,
             lambda = NULL, nlambda = 30, 
             lambda.min = 1e-5, intercept = FALSE,
             control = list("abstol" = abstol, 
                            "reltol" = reltol, 
                            "adaptation" = rho_adaptation, 
                            "rho" = rho, 
                            "print.out" = FALSE))
                                    
err_mod <- apply(mod$sp.coef.path, 1, function(x) sum((x - x_0)^2))
plot(log(mod$lambda), err_mod, type = "l", col = "blue", 
     lwd = 2, xlab = latex2exp::TeX("$\\log(\\lambda)$"), 
     ylab = "Estimation Error", main = "True Estimation Error", bty = "n")
abline(v = log(mod$lambda[which(err_mod == min(err_mod))]), col = "red", lwd = 1.0)
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0, lty = 2)                                      

Sparse Adaptive Overlap Group Least Absolute Shrinkage and Selection Operator

Description

Sparse Adaptive overlap group-LASSO, or sparse adaptive group L_2-regularized regression, solves the following optimization problem

\textrm{min}_{\beta,\gamma} ~ \frac{1}{2}\|y-X\beta-Z\gamma\|_2^2 + \lambda\Big[(1-\alpha) \sum_{g=1}^G \|S_g T\beta\|_2+\alpha\Vert T_1\beta\Vert_1\Big]

to obtain a sparse coefficient vector \beta\in\mathbb{R}^p for the matrix of penalized predictors X and a coefficient vector \gamma\in\mathbb{R}^q for the matrix of unpenalized predictors Z. For each group g, each row of the matrix S_g\in\mathbb{R}^{n_g\times p} has non-zero entries only for those variables belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each variable can belong to more than one group. The diagonal matrix T\in\mathbb{R}^{p\times p} contains the variable-specific weights. These values are provided by the argument var_weights (see below). The diagonal matrix T_1\in\mathbb{R}^{p\times p} contains the variable-specific L_1 weights. These values are provided by the argument var_weights_L1 (see below). The regularization path is computed for the sparse adaptive overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method. The regularization is a combination of L_2 and L_1 simultaneous constraints. Different specifications of the penalty argument lead to different models choice:

LASSO

The classical Lasso regularization (Tibshirani, 1996) can be obtained by specifying \alpha = 1 and the matrix T_1 as the p \times p identity matrix. An adaptive version of this model (Zou, 2006) can be obtained if T_1 is a p \times p diagonal matrix of adaptive weights. See also Hastie et al. (2015) for further details.

GLASSO

The group-Lasso regularization (Yuan and Lin, 2006) can be obtained by specifying \alpha = 0, non-overlapping groups in S_g and by setting the matrix T equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrix T is a p \times p diagonal matrix of adaptive weights. See also Hastie et al. (2015) for further details.

spGLASSO

The sparse group-Lasso regularization (Simon et al., 2011) can be obtained by specifying \alpha\in(0,1), non-overlapping groups in S_g and by setting the matrices T and T_1 equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrices T and T_1 are p \times p diagonal matrices of adaptive weights.

OVGLASSO

The overlap group-Lasso regularization (Jenatton et al., 2011) can be obtained by specifying \alpha = 0, overlapping groups in S_g and by setting the matrix T equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrix T is a p \times p diagonal matrix of adaptive weights.

spOVGLASSO

The sparse overlap group-Lasso regularization (Jenatton et al., 2011) can be obtained by specifying \alpha\in(0,1), overlapping groups in S_g and by setting the matrices T and T_1 equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrices T and T_1 are p \times p diagonal matrices of adaptive weights.

Usage

lmSP(
  X,
  Z = NULL,
  y,
  penalty = c("LASSO", "GLASSO", "spGLASSO", "OVGLASSO", "spOVGLASSO"),
  groups,
  group_weights = NULL,
  var_weights = NULL,
  var_weights_L1 = NULL,
  standardize.data = TRUE,
  intercept = FALSE,
  overall.group = FALSE,
  lambda = NULL,
  alpha = NULL,
  lambda.min.ratio = NULL,
  nlambda = 30,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

a length-p solution vector for the parameters \beta. If n_\lambda>1 then the provided vector corresponds to the minimum in-sample MSE.

coefficients

a length-q solution vector for the parameters \gamma. If n_\lambda>1 then the provided vector corresponds to the minimum in-sample MSE. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

sp.coef.path

an (n_\lambda\times p) matrix of estimated \beta coefficients for each lambda of the provided sequence.

coef.path

an (n_\lambda\times q) matrix of estimated \gamma coefficients for each lambda of the provided sequence. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the minimum in sample MSE.

mse

in-sample mean squared error.

min.mse

minimum value of the in-sample MSE for the sequence of lambda.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

When you run the algorithm, output returns not only the solution, but also the iteration history recording following fields over iterates:

objval

objective function value

r_norm

norm of primal residual

s_norm

norm of dual residual

eps_pri

feasibility tolerance for primal feasibility condition

eps_dual

feasibility tolerance for dual feasibility condition.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Hastie T, Tibshirani R, Wainwright M (2015). Statistical learning with sparsity: the lasso and generalizations, number 143 in Monographs on statistics and applied probability. CRC Press, Taylor & Francis Group, Boca Raton. ISBN 978-1-4987-1216-3.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Simon N, Friedman J, Hastie T, Tibshirani R (2013). “A sparse-group lasso.” J. Comput. Graph. Statist., 22(2), 231–245. ISSN 1061-8600, doi:10.1080/10618600.2012.681250.

Yuan M, Lin Y (2006). “Model selection and estimation in regression with grouped variables.” Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68(1), 49–67.

Zou H (2006). “The adaptive lasso and its oracle properties.” J. Amer. Statist. Assoc., 101(476), 1418–1429. ISSN 0162-1459, doi:10.1198/016214506000000735.

Examples

### generate sample data
set.seed(2023)
n    <- 50
p    <- 30 
X    <- matrix(rnorm(n*p), n, p)

### Example 1, LASSO penalty

beta <- apply(matrix(rnorm(p, sd = 1), p, 1), 1, fdaSP::softhresh, 1.5)
y    <- X %*% beta + rnorm(n, sd = sqrt(crossprod(X %*% beta)) / 20)

### set regularization parameter grid
lam   <- 10^seq(0, -2, length.out = 30)

### set the hyper-parameters of the ADMM algorithm
maxit      <- 1000
adaptation <- TRUE
rho        <- 1
reltol     <- 1e-5
abstol     <- 1e-5

### run example
mod <- lmSP(X = X, y = y, penalty = "LASSO", standardize.data = FALSE, intercept = FALSE, 
            lambda = lam, control = list("adaptation" = adaptation, "rho" = rho, 
                                         "maxit" = maxit, "reltol" = reltol, 
                                         "abstol" = abstol, "print.out" = FALSE)) 

### graphical presentation
matplot(log(lam), mod$sp.coef.path, type = "l", main = "Lasso solution path",
        bty = "n", xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "")

### Example 2, sparse group-LASSO penalty

beta <- c(rep(4, 12), rep(0, p - 13), -2)
y    <- X %*% beta + rnorm(n, sd = sqrt(crossprod(X %*% beta)) / 20)

### define groups of dimension 3 each
group1 <- rep(1:10, each = 3)

### set regularization parameter grid
lam   <- 10^seq(1, -2, length.out = 30)

### set the alpha parameter 
alpha <- 0.5

### set the hyper-parameters of the ADMM algorithm
maxit         <- 1000
adaptation    <- TRUE
rho           <- 1
reltol        <- 1e-5
abstol        <- 1e-5

### run example
mod <- lmSP(X = X, y = y, penalty = "spGLASSO", groups = group1, standardize.data = FALSE,  
            intercept = FALSE, lambda = lam, alpha = 0.5, 
            control = list("adaptation" = adaptation, "rho" = rho, 
                           "maxit" = maxit, "reltol" = reltol, "abstol" = abstol, 
                           "print.out" = FALSE)) 

### graphical presentation
matplot(log(lam), mod$sp.coef.path, type = "l", main = "Sparse Group Lasso solution path",
        bty = "n", xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "")

Cross-validation for Sparse Adaptive Overlap Group Least Absolute Shrinkage and Selection Operator

Description

Sparse Adaptive overlap group-LASSO, or sparse adaptive group L_2-regularized regression, solves the following optimization problem

\textrm{min}_{\beta,\gamma} ~ \frac{1}{2}\|y-X\beta-Z\gamma\|_2^2 + \lambda\Big[(1-\alpha) \sum_{g=1}^G \|S_g T\beta\|_2+\alpha\Vert T_1\beta\Vert_1\Big]

to obtain a sparse coefficient vector \beta\in\mathbb{R}^p for the matrix of penalized predictors X and a coefficient vector \gamma\in\mathbb{R}^q for the matrix of unpenalized predictors Z. For each group g, each row of the matrix S_g\in\mathbb{R}^{n_g\times p} has non-zero entries only for those variables belonging to that group. These values are provided by the arguments groups and group_weights (see below). Each variable can belong to more than one group. The diagonal matrix T\in\mathbb{R}^{p\times p} contains the variable-specific weights. These values are provided by the argument var_weights (see below). The diagonal matrix T_1\in\mathbb{R}^{p\times p} contains the variable-specific L_1 weights. These values are provided by the argument var_weights_L1 (see below). The regularization path is computed for the sparse adaptive overlap group-LASSO penalty at a grid of values for the regularization parameter \lambda using the alternating direction method of multipliers (ADMM). See Boyd et al. (2011) and Lin et al. (2022) for details on the ADMM method. The regularization is a combination of L_2 and L_1 simultaneous constraints. Different specifications of the penalty argument lead to different models choice:

LASSO

The classical Lasso regularization (Tibshirani, 1996) can be obtained by specifying \alpha = 1 and the matrix T_1 as the p \times p identity matrix. An adaptive version of this model (Zou, 2006) can be obtained if T_1 is a p \times p diagonal matrix of adaptive weights. See also Hastie et al. (2015) for further details.

GLASSO

The group-Lasso regularization (Yuan and Lin, 2006) can be obtained by specifying \alpha = 0, non-overlapping groups in S_g and by setting the matrix T equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrix T is a p \times p diagonal matrix of adaptive weights. See also Hastie et al. (2015) for further details.

spGLASSO

The sparse group-Lasso regularization (Simon et al., 2011) can be obtained by specifying \alpha\in(0,1), non-overlapping groups in S_g and by setting the matrices T and T_1 equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrices T and T_1 are p \times p diagonal matrices of adaptive weights.

OVGLASSO

The overlap group-Lasso regularization (Jenatton et al., 2011) can be obtained by specifying \alpha = 0, overlapping groups in S_g and by setting the matrix T equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrix T is a p \times p diagonal matrix of adaptive weights.

spOVGLASSO

The sparse overlap group-Lasso regularization (Jenatton et al., 2011) can be obtained by specifying \alpha\in(0,1), overlapping groups in S_g and by setting the matrices T and T_1 equal to the p \times p identity matrix. An adaptive version of this model can be obtained if the matrices T and T_1 are p \times p diagonal matrices of adaptive weights.

Usage

lmSP_cv(
  X,
  Z = NULL,
  y,
  penalty = c("LASSO", "GLASSO", "spGLASSO", "OVGLASSO", "spOVGLASSO"),
  groups,
  group_weights = NULL,
  var_weights = NULL,
  var_weights_L1 = NULL,
  cv.fold = 5,
  standardize.data = TRUE,
  intercept = FALSE,
  overall.group = FALSE,
  lambda = NULL,
  alpha = NULL,
  lambda.min.ratio = NULL,
  nlambda = 30,
  control = list()
)

Arguments

Value

A named list containing

sp.coefficients

a length-p solution vector for the parameters \beta. If n_\lambda>1 then the provided vector corresponds to the minimum cross-validated MSE.

coefficients

a length-q solution vector for the parameters \gamma. If n_\lambda>1 then the provided vector corresponds to the minimum cross-validated MSE. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

sp.coef.path

an (n_\lambda\times p) matrix of estimated \beta coefficients for each lambda of the provided sequence.

coef.path

an (n_\lambda\times q) matrix of estimated \gamma coefficients for each lambda of the provided sequence. It is provided only when either the matrix Z in input is not NULL or the intercept is set to TRUE.

lambda

sequence of lambda.

lambda.min

value of lambda that attains the minimum cross-validated MSE.

mse

cross-validated mean squared error.

min.mse

minimum value of the cross-validated MSE for the sequence of lambda.

convergence

logical. 1 denotes achieved convergence.

elapsedTime

elapsed time in seconds.

iternum

number of iterations.

When you run the algorithm, output returns not only the solution, but also the iteration history recording following fields over iterates:

objval

objective function value

r_norm

norm of primal residual

s_norm

norm of dual residual

eps_pri

feasibility tolerance for primal feasibility condition

eps_dual

feasibility tolerance for dual feasibility condition.

Iteration stops when both r_norm and s_norm values become smaller than eps_pri and eps_dual, respectively.

Details

The control argument is a list that can supply any of the following components:

adaptation

logical. If it is TRUE, ADMM with adaptation is performed. The default value is TRUE. See Boyd et al. (2011) for details.

rho

an augmented Lagrangian parameter. The default value is 1.

tau.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 2. See Boyd et al. (2011) for details.

mu.ada

an adaptation parameter greater than one. Only needed if adaptation = TRUE. The default value is 10. See Boyd et al. (2011) for details.

abstol

absolute tolerance stopping criterion. The default value is sqrt(sqrt(.Machine$double.eps)).

reltol

relative tolerance stopping criterion. The default value is sqrt(.Machine$double.eps).

maxit

maximum number of iterations. The default value is 100.

print.out

logical. If it is TRUE, a message about the procedure is printed. The default value is TRUE.

References

Bernardi M, Canale A, Stefanucci M (2022). “Locally Sparse Function-on-Function Regression.” Journal of Computational and Graphical Statistics, 0(0), 1-15. doi:10.1080/10618600.2022.2130926, https://doi.org/10.1080/10618600.2022.2130926.

Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011). “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers.” Foundations and Trends® in Machine Learning, 3(1), 1-122. ISSN 1935-8237, doi:10.1561/2200000016, http://dx.doi.org/10.1561/2200000016.

Hastie T, Tibshirani R, Wainwright M (2015). Statistical learning with sparsity: the lasso and generalizations, number 143 in Monographs on statistics and applied probability. CRC Press, Taylor & Francis Group, Boca Raton. ISBN 978-1-4987-1216-3.

Jenatton R, Audibert J, Bach F (2011). “Structured variable selection with sparsity-inducing norms.” J. Mach. Learn. Res., 12, 2777–2824. ISSN 1532-4435.

Lin Z, Li H, Fang C (2022). Alternating direction method of multipliers for machine learning. Springer, Singapore. ISBN 978-981-16-9839-2; 978-981-16-9840-8, doi:10.1007/978-981-16-9840-8, With forewords by Zongben Xu and Zhi-Quan Luo.

Simon N, Friedman J, Hastie T, Tibshirani R (2013). “A sparse-group lasso.” J. Comput. Graph. Statist., 22(2), 231–245. ISSN 1061-8600, doi:10.1080/10618600.2012.681250.

Yuan M, Lin Y (2006). “Model selection and estimation in regression with grouped variables.” Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68(1), 49–67.

Zou H (2006). “The adaptive lasso and its oracle properties.” J. Amer. Statist. Assoc., 101(476), 1418–1429. ISSN 0162-1459, doi:10.1198/016214506000000735.

Examples

### generate sample data
set.seed(2023)
n    <- 50
p    <- 30 
X    <- matrix(rnorm(n * p), n, p)

### Example 1, LASSO penalty

beta <- apply(matrix(rnorm(p, sd = 1), p, 1), 1, fdaSP::softhresh, 1.5)
y    <- X %*% beta + rnorm(n, sd = sqrt(crossprod(X %*% beta)) / 20)

### set the hyper-parameters of the ADMM algorithm
maxit      <- 1000
adaptation <- TRUE
rho        <- 1
reltol     <- 1e-5
abstol     <- 1e-5

### run cross-validation
mod_cv <- lmSP_cv(X = X, y = y, penalty = "LASSO", 
                  standardize.data = FALSE, intercept = FALSE,
                  cv.fold = 5, nlambda = 30, 
                  control = list("adaptation" = adaptation, 
                                 "rho" = rho, 
                                 "maxit" = maxit, "reltol" = reltol, 
                                 "abstol" = abstol, 
                                 "print.out" = FALSE)) 

### graphical presentation
plot(log(mod_cv$lambda), mod_cv$mse, type = "l", col = "blue", lwd = 2, bty = "n", 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "Prediction Error", 
     ylim = range(mod_cv$mse - mod_cv$mse.sd, mod_cv$mse + mod_cv$mse.sd),
     main = "Cross-validated Prediction Error")
fdaSP::confband(xV = log(mod_cv$lambda), yVmin = mod_cv$mse - mod_cv$mse.sd, 
                yVmax = mod_cv$mse + mod_cv$mse.sd)       
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0)

### comparison with oracle error
mod <- lmSP(X = X, y = y, penalty = "LASSO", 
            standardize.data = FALSE, 
            intercept = FALSE,
            nlambda = 30, 
            control = list("adaptation" = adaptation, 
                           "rho" = rho, 
                           "maxit" = maxit, "reltol" = reltol, 
                           "abstol" = abstol, 
                           "print.out" = FALSE)) 
                                         
err_mod <- apply(mod$sp.coef.path, 1, function(x) sum((x - beta)^2))
plot(log(mod$lambda), err_mod, type = "l", col = "blue", lwd = 2, 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), 
     ylab = "Estimation Error", main = "True Estimation Error", bty = "n")
abline(v = log(mod$lambda[which(err_mod == min(err_mod))]), col = "red", lwd = 1.0)
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0, lty = 2)

### Example 2, sparse group-LASSO penalty

beta <- c(rep(4, 12), rep(0, p - 13), -2)
y    <- X %*% beta + rnorm(n, sd = sqrt(crossprod(X %*% beta)) / 20)

### define groups of dimension 3 each
group1 <- rep(1:10, each = 3)

### set regularization parameter grid
lam   <- 10^seq(1, -2, length.out = 30)

### set the alpha parameter 
alpha <- 0.5

### set the hyper-parameters of the ADMM algorithm
maxit         <- 1000
adaptation    <- TRUE
rho           <- 1
reltol        <- 1e-5
abstol        <- 1e-5

### run cross-validation
mod_cv <- lmSP_cv(X = X, y = y, penalty = "spGLASSO", 
                  groups = group1, cv.fold = 5, 
                  standardize.data = FALSE,  intercept = FALSE, 
                  lambda = lam, alpha = 0.5, 
                  control = list("adaptation" = adaptation, 
                                 "rho" = rho,
                                 "maxit" = maxit, "reltol" = reltol, 
                                 "abstol" = abstol, 
                                 "print.out" = FALSE)) 

### graphical presentation
plot(log(mod_cv$lambda), mod_cv$mse, type = "l", col = "blue", lwd = 2, bty = "n", 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), ylab = "Prediction Error", 
     ylim = range(mod_cv$mse - mod_cv$mse.sd, mod_cv$mse + mod_cv$mse.sd),
     main = "Cross-validated Prediction Error")
fdaSP::confband(xV = log(mod_cv$lambda), yVmin = mod_cv$mse - mod_cv$mse.sd, 
                yVmax = mod_cv$mse + mod_cv$mse.sd)       
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0)

### comparison with oracle error
mod <- lmSP(X = X, y = y, 
            penalty = "spGLASSO", 
            groups = group1, 
            standardize.data = FALSE, 
            intercept = FALSE,
            lambda = lam, 
            alpha = 0.5, 
            control = list("adaptation" = adaptation, "rho" = rho, 
                           "maxit" = maxit, "reltol" = reltol, "abstol" = abstol, 
                           "print.out" = FALSE)) 
                                         
err_mod <- apply(mod$sp.coef.path, 1, function(x) sum((x - beta)^2))
plot(log(mod$lambda), err_mod, type = "l", col = "blue", lwd = 2, 
     xlab = latex2exp::TeX("$\\log(\\lambda)$"), 
     ylab = "Estimation Error", main = "True Estimation Error", bty = "n")
abline(v = log(mod$lambda[which(err_mod == min(err_mod))]), col = "red", lwd = 1.0)
abline(v = log(mod_cv$lambda[which(mod_cv$lambda == mod_cv$lambda.min)]), 
       col = "red", lwd = 1.0, lty = 2)

Function to solve the soft thresholding problem

Description

Function to solve the soft thresholding problem

Usage

softhresh(x, lambda)

Arguments

Value

the solution to the soft thresholding operator.

References

Hastie T, Tibshirani R, Wainwright M (2015). Statistical learning with sparsity: the lasso and generalizations, number 143 in Monographs on statistics and applied probability. CRC Press, Taylor & Francis Group, Boca Raton. ISBN 978-1-4987-1216-3.