Skip to content
ml-recall

#huber-loss

1 question from Linear Models & Regularization

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedLinear Models & Regularization

The Huber loss with threshold σ\sigma is l(r)=r22σl(r) = \frac{r^2}{2\sigma} for ∣r∣≤σ|r| \le \sigma and l(r)=∣r∣−σ2l(r) = |r| - \frac{\sigma}{2} otherwise, where r=y^−yr = \hat y - y is the residual. With σ=2\sigma = 2, the derivative dl/drdl/dr is for a residual r=1.5r = 1.5 and for an outlier with r=500r = 500.

Fill in every blank (hints in the boxes). Enter moves to the next blank.