RegressionFactory

Expander Functions for Generating Full Gradient and Hessian from Single-Slot and Multi-Slot Base Distributions

v0.7.4 · Oct 25, 2020 · GPL (>= 2)

Description

The expander functions rely on the mathematics developed for the Hessian-definiteness invariance theorem for linear projection transformations of variables, described in authors' paper, to generate the full, high-dimensional gradient and Hessian from the lower-dimensional derivative objects. This greatly relieves the computational burden of generating the regression-function derivatives, which in turn can be fed into any optimization routine that utilizes such derivatives. The theorem guarantees that Hessian definiteness is preserved, meaning that reasoning about this property can be performed in the low-dimensional space of the base distribution. This is often a much easier task than its equivalent in the full, high-dimensional space. Definiteness of Hessian can be useful in selecting optimization/sampling algorithms such as Newton-Raphson optimization or its sampling equivalent, the Stochastic Newton Sampler. Finally, in addition to being a computational tool, the regression expansion framework is of conceptual value by offering new opportunities to generate novel regression problems.

Downloads

233

Last 30 days

13915th

233

Last 90 days

233

Last year

CRAN Check Status

14 NOTE

Show all 14 flavors

Flavor	Status	Time
r-devel-linux-x86_64-debian-clang	NOTE	31.8s
r-devel-linux-x86_64-debian-gcc	NOTE	24.6s
r-devel-linux-x86_64-fedora-clang	NOTE	47.8s
r-devel-linux-x86_64-fedora-gcc	NOTE	57.7s
r-devel-macos-arm64	NOTE	17s
r-devel-windows-x86_64	NOTE	69s
r-oldrel-macos-arm64	NOTE
r-oldrel-macos-x86_64	NOTE	37s
r-oldrel-windows-x86_64	NOTE	73s
r-patched-linux-x86_64	NOTE	28.5s
r-release-linux-x86_64	NOTE	28.5s
r-release-macos-arm64	NOTE
r-release-macos-x86_64	NOTE	40s
r-release-windows-x86_64	NOTE	69s

Check details (16 non-OK)

NOTE r-devel-linux-x86_64-debian-clang

CRAN incoming feasibility

Maintainer: ‘Alireza S. Mahani <alireza.s.mahani@gmail.com>’

No Authors@R field in DESCRIPTION.
Please add one, modifying
  Authors@R: c(person(given = c("Alireza", "S."),
                      family = "Mahani",
                      role = c("aut", "cre"),
                      email = "alireza.s.mahani@gmail.com"),
               person(given = c("Mansour", "T.A."),
                      family = "Sharabiani",
                      role = "aut"))
as necessary.

NOTE r-devel-linux-x86_64-debian-clang

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-devel-linux-x86_64-debian-gcc

CRAN incoming feasibility

Maintainer: ‘Alireza S. Mahani <alireza.s.mahani@gmail.com>’

No Authors@R field in DESCRIPTION.
Please add one, modifying
  Authors@R: c(person(given = c("Alireza", "S."),
                      family = "Mahani",
                      role = c("aut", "cre"),
                      email = "alireza.s.mahani@gmail.com"),
               person(given = c("Mansour", "T.A."),
                      family = "Sharabiani",
                      role = "aut"))
as necessary.

NOTE r-devel-linux-x86_64-debian-gcc

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-devel-linux-x86_64-fedora-clang

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-devel-linux-x86_64-fedora-gcc

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-devel-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-devel-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-oldrel-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-oldrel-macos-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-oldrel-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-patched-linux-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-release-linux-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-release-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-release-macos-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

NOTE r-release-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. Users can write thin wrappers around these functions to add the constant terms to the function value. (Derivatives do not need correction. For binomial family, all factorial terms are ignored since they only depend on \code{n} and {y}.)
       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ^

Check History

NOTE 0 OK · 14 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE Mar 9, 2026

NOTE r-devel-linux-x86_64-debian-clang

CRAN incoming feasibility

Maintainer: ‘Alireza S. Mahani <alireza.s.mahani@gmail.com>’

No Authors@R field in DESCRIPTION.
Please add one, modifying
  Authors@R: c(person(given = c("Alireza", "S."),
                      family = "Mahani",
                      role = c("aut", "cre"),
                      email = "alireza.s.mahani@gmail.com"),
               person(given = c("Mansour", "T.A."),
                      family = "Sharabiani",
                      role = "aut"))
as necessary.

NOTE r-devel-linux-x86_64-debian-gcc

CRAN incoming feasibility

Maintainer: ‘Alireza S. Mahani <alireza.s.mahani@gmail.com>’

No Authors@R field in DESCRIPTION.
Please add one, modifying
  Authors@R: c(person(given = c("Alireza", "S."),
                      family = "Mahani",
                      role = c("aut", "cre"),
                      email = "alireza.s.mahani@gmail.com"),
               person(given = c("Mansour", "T.A."),
                      family = "Sharabiani",
                      role = "aut"))
as necessary.

NOTE r-devel-linux-x86_64-fedora-clang

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-devel-linux-x86_64-fedora-gcc

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-devel-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-devel-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-patched-linux-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-release-linux-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-release-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-release-macos-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-release-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-oldrel-macos-arm64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-oldrel-macos-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

NOTE r-oldrel-windows-x86_64

Rd files

checkRd: (-1) fbase1.binomial.Rd:32: Lost braces; missing escapes or markup?
    32 | In all base log-likelihood functions, we have dropped any additive terms that are independent of the distribution parameter, e.g. constant terms or those terms that are dependent on the response variable only. This is done for computational efficiency. Therefore, these functions cannot be used to obtain the absolute values of log-likelihood functions but only in the context of optimization and/or sampling. User

RegressionFactory

Description

Downloads

CRAN Check Status

Check History

Reverse Dependencies (1)

suggests

Dependency Network

Version History