copt.SquaredLoss

class copt.SquaredLoss(A, b, alpha=0, intercept=False)[source]

Least squares loss function with L2 regularization

Parameters:
  • A (ndarray or LinearOperator) – Design matrix. If None, it is taken as the identity matrix.
  • b (ndarray) –
  • alpha (float) – Amount of L2 regularization
__init__(A, b, alpha=0, intercept=False)[source]

Methods

__init__(A, b[, alpha, intercept])
gradient(x)
lipschitz_constant([kind])
partial_gradient_factory()