Huber Loss
~15 mincode completion
Implement huber_loss(y_true, y_pred, delta) that returns the mean Huber loss over all samples.
Examples
Small errors (< delta): quadratic MSE regime
- Input
- huber_loss([0, 0], [0.5, -0.5], 1)
- Output
- 0.125
Large error (> delta): linear MAE regime
- Input
- huber_loss([0], [5], 1)
- Output
- 4.5
At boundary (|r| = delta): quadratic result
- Input
- huber_loss([0], [1], 1)
- Output
- 0.5
Hints
Hint 1
picks between two values elementwise without branching.
Hint 2
Watch for this: used mse formula for all.
Requirements
y_true: Ground truth values, shape (m,)y_pred: Predicted values, shape (m,)delta: Threshold between quadratic and linear regimesReturn Scalar mean Huber loss.
Constraints
Allowed library: NumPy only
Time limit: 200 ms, Memory: 64 MB
Try similar problems(4)
Where this shows up
~15 min
••••••••••••••••
8 employers weight this skill
3 frontier labs, 2 big tech firms, 2 autonomy companies, 1 enterprise vendor. Top match scores 63.
Python
import numpy as np
def huber_loss(y_true: np.ndarray, y_pred: np.ndarray, delta: float) -> float:
"""
Compute the mean Huber loss.
Args:
y_true: Ground truth values, shape (m,)
y_pred: Predicted values, shape (m,)
delta: Threshold between quadratic and linear regimes
Returns:
Scalar mean Huber loss.
"""
# YOUR CODE HERE
pass