Least Absolute Shrinkage and Selection Operator (LASSO)
Least Absolute Shrinkage and Selection Operator (LASSO) is a method
for modeling relationship between a dependent variable (which may be
a vector) and one or more explanatory variables by fitting
regularized least squares model. Trained LASSO model can produce
sparse coefficients due to the use of
regularization
term. LASSO regression is widely used in feature selection tasks. For
example, in the field of compressed sensing it is used to effectively
identify relevant features associated with the dependent variable
from a few observations with a large number of features. LASSO
regression is also used to overcome multicollinearity of feature
vectors in the training data set.
Details
Let
be a vector of input variables and
be the response.
For each
, the LASSO model has the form similar to linear and ridge regression model [Hoerl70],
except that the coefficients are trained by minimizing a regularized by
penalty mean squared error (MSE)
objective function.
Here
,
are referred to as independent variables,
is referred to as dependent variable or response and
.
Training Stage
Let
be a set of
training data (for regression task,
, and for feature selection
could be greater than
).
The matrix
of size
contains observations
,
,
of independent variables.
For each
,
, the LASSO regression estimates
by minimizing the objective function:
In the equation above, the first term is a mean squared error function and the second one is a regularization term that
penalizes the
norm of vector 
For more details, see [Hastie2009].
By default, Coordinate Descent iterative solver is used to minimize the objective
function. SAGA solver is also applicable for minimization.
Prediction Stage
For input vector of independent variables
, prediction based on LASSO regression is done using the equation
where
.