Linear and probabilistic models · MLD-0626
Lasso
Regression using an L1 penalty that can set coefficients exactly to zero.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Select a sparse subset of predictive features.
Original caveat
Selection can be unstable among strongly correlated features.
Context and aliases
Level: Intermediate. Stages: Training · Inference.
Tags: ML.
Aliases: Least absolute shrinkage and selection operator.
Related concepts
Concepts linking here
Original references
- scikit-learn: Gaussian processes ↗ · Reference link
- scikit-learn: linear models ↗ · Reference link
- scikit-learn: naive Bayes ↗ · Reference link
- Original reference URL ↗