loss2: Composite Loss Value

In mpath: Regularized Linear Models

Composite Loss Value

Description

Compute composite loss value

Usage

loss2(y, f, weights, cfun, dfun, s, delta=0.0001)

Arguments

y	response variable values
f	linear predictor values of y. If f is predicted response of model, use function loss3 instead
weights	observation weights, same length as y
cfun	integer from 1-8, concave function as in irglm_fit
dfun	integer from 1-7, convex function as in irglm_fit
s	tuning parameter of cfun. s > 0 and can be equal to 0 for cfun="tcave".
delta	a small positive number provided by user only if cfun="gcave" and 0 < s <1

Details

An internal function. For large s values, the loss can be 0 with cfun=2,3,4, or "acave", "bcave", "ccave".

Value

Weighted loss values

Author(s)

Zhu Wang <[e-mail]>

References

Zhu Wang (2020) Unified Robust Estimation, arXiv e-prints, https://arxiv.org/abs/2010.02848

See Also

loss3 irglm irglmreg loss2_irsvm

mpath documentation built on Jan. 7, 2023, 1:17 a.m.