What is Lasso Regression?
Updated May 16, 2026
Short answer
Lasso uses L1 regularization to shrink some coefficients to zero, enabling feature selection.
Deep explanation
It adds λ∑|β| to the loss, encouraging sparsity. This makes it useful when many features are irrelevant, effectively performing automatic feature selection.
Real-world example
Used in genomics for selecting relevant genes.
Common mistakes
- Not standardizing features before applying Lasso.
Follow-up questions
- Why does L1 create sparsity?
- Can Lasso handle multicollinearity?