cost

cost,oscar-methods

cost,oscar-method

Return total cost of model fit based on provided kit/variable costs vector
Return total cost of model fit based on provided kit/variable costs vector

Optimal Subset Cardinality Regression (OSCAR) models offer
regularized linear regression using the L0-pseudonorm, conventionally
known as the number of non-zero coefficients. The package estimates an
optimal subset of features using the L0-penalization via
cross-validation, bootstrapping and visual diagnostics. Effective
Fortran implementations are offered along the package for finding
optima for the DC-decomposition, which is used for transforming the
discrete L0-regularized optimization problem into a continuous
non-convex optimization task. These optimization modules include DBDC
('Double Bundle method for nonsmooth DC optimization' as described in
Joki et al. (2018) <doi:10.1137/16M1115733>) and LMBM ('Limited
Memory Bundle Method for large-scale nonsmooth optimization' as
in Haarala et al. (2004) <doi:10.1080/10556780410001689225>). The
OSCAR models are comprehensively exemplified in Halkola et al. (2023)
<doi:10.1371/journal.pcbi.1010333>). Multiple regression model families
are supported: Cox, logistic, and Gaussian.

Teemu Daniel Laajala

oscar

Optimal Subset Cardinality Regression (OSCAR) Models Using the
L0-Pseudonorm

Kaisa Joki

Anni Halkola

cost function

<dl><dt>object</dt>
<dd>Fit oscar S4-object</dd>
<dt>k</dt>
<dd>Cardinality 'k' to compute total feature cost at</dd></dl>

Arguments

Return total cost of model fit based on provided kit/variable costs vector — cost

<dl>

<dt>object</dt>
<dd>Fit oscar S4-object</dd>


<dt>k</dt>
<dd>Cardinality 'k' to compute total feature cost at</dd>

</dl>

cost: Return total cost of model fit based on provided kit/variable costs vector

Description

Usage

Value

Arguments