Function compute_lambda_max 

pub fn compute_lambda_max(
    x: &Matrix,
    y: &[f64],
    alpha: f64,
    penalty_factor: Option<&[f64]>,
    intercept_col: Option<usize>,
) -> f64

Computes lambda_max: the smallest lambda for which all penalized coefficients are zero.

For lasso (alpha > 0), lambda_max is the smallest value such that the soft-thresholding operation zeros out all coefficients.

For standardized X and centered y:

lambda_max = max_j |x_j^T y| / (n * alpha)

Arguments

• x - Standardized design matrix (n × p), first column is intercept if present
• y - Centered response vector (n elements)
• alpha - Elastic net mixing parameter
• penalty_factor - Per-feature penalty factors (optional, defaults to all 1.0)
• intercept_col - Index of intercept column (typically 0, or None if no intercept)

Returns

The maximum lambda value for the path.

Note

If alpha = 0 (pure ridge), this returns f64::INFINITY since ridge never produces exact zero coefficients. Use make_lambda_path which handles this case by using a small alpha value.