|
gptkbp:instanceOf
|
gptkb:regression_analysis_method
gptkb:statistical_analysis
|
|
gptkbp:alsoKnownAs
|
gptkb:Least_Absolute_Shrinkage_and_Selection_Operator
|
|
gptkbp:application
|
gptkb:signal_processing
finance
genomics
image analysis
|
|
gptkbp:feature
|
can shrink some coefficients to zero
performs feature selection
|
|
gptkbp:form
|
minimize (1/2n)||y - Xβ||^2_2 + λ||β||_1
|
|
gptkbp:hyperparameter
|
lambda (regularization parameter)
|
|
gptkbp:implementedIn
|
gptkb:MATLAB
gptkb:scikit-learn
R
|
|
gptkbp:introduced
|
gptkb:Robert_Tibshirani
|
|
gptkbp:introducedIn
|
1996
|
|
gptkbp:limitation
|
can select at most n variables if n < p
can be unstable with highly correlated predictors
|
|
gptkbp:objective
|
minimize sum of squared errors plus lambda times sum of absolute values of coefficients
|
|
gptkbp:penalty
|
L1 norm
|
|
gptkbp:relatedTo
|
gptkb:elastic_net
ridge regression
|
|
gptkbp:solvedBy
|
gptkb:least_angle_regression_(LARS)
coordinate descent
subgradient methods
|
|
gptkbp:usedFor
|
regularization
variable selection
preventing overfitting
|
|
gptkbp:usedIn
|
gptkb:machine_learning
statistics
|
|
gptkbp:bfsParent
|
gptkb:Regression_analysis
|
|
gptkbp:bfsLayer
|
6
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
lasso regression
|