Chunk #43 — 4 Regularized Multinomial Regression — 4.1 Regularization and Parameter Ambiguity

Source

Regularization Paths for Generalized Linear Models via Coordinate Descent.

Embedded

yes

Text

This can be done separately for each coordinate, hence (28)cj=argmint∑ℓ=1K[12(1−α)(βjℓ−t)2+α|βjℓ−t|].