Laurae (version 0.0.0.9001)

loss_MSE_grad: Mean Squared Error (gradient function)

Description

This function computes the Mean Squared Error loss (MSE) gradient per value provided preds and labels.

Usage

loss_MSE_grad(y_pred, y_true)

Arguments

y_pred

The predictions.

y_true

The labels.

Value

The gradient of the Squared Error per value.

Details

Supposing: \(x = preds - labels\) Loss Formula : \(x^2\) Gradient Formula : \(2 * x\) Hessian Formula : \(2\)