Function robust_least_squares 

pub fn robust_least_squares<F, J, L, D, S1, S2>(
    residuals: F,
    x0: &ArrayBase<S1, Ix1>,
    loss: L,
    jacobian: Option<J>,
    data: &ArrayBase<S2, Ix1>,
    options: Option<RobustOptions>,
) -> OptimizeResult<OptimizeResults<f64>>
where
    F: Fn(&[f64], &[D]) -> Array1<f64>,
    J: Fn(&[f64], &[D]) -> Array2<f64>,
    L: RobustLoss,
    D: Clone,
    S1: Data<Elem = f64>,
    S2: Data<Elem = D>,

Solve a robust least squares problem using M-estimators

This function minimizes the sum of a robust loss function applied to residuals, providing protection against outliers in the data.

Arguments

• residuals - Function that returns the residuals
• x0 - Initial guess for the parameters
• loss - Robust loss function to use
• jacobian - Optional Jacobian function
• data - Additional data to pass to residuals and jacobian
• options - Options for the optimization