loss_sharp_res: Sharp Loss Function Exact loss function without gradients for...
In edahelsinki/slise: Sparse Linear Subset Explanations

loss_sharp_res

R Documentation

Sharp Loss Function Exact loss function without gradients for when the residuals are already calculated

Sharp Loss Function Exact loss function without gradients for when the residuals are already calculated

loss_sharp_res(
  alpha,
  residuals2,
  epsilon2,
  lambda1 = 0,
  lambda2 = 0,
  weight = NULL
)

`alpha`	The vector to calculate loss for
`residuals2`	The squared error vector: (X %*% alpha - Y)^2
`epsilon2`	The squared acceptable error
`lambda1`	The L1 regulariser (default: 0)
`lambda2`	The L2 regulariser (default: 0)
`weight`	weight vector (default: NULL)