Which relationship between training and dev error is usual for a learning algorithm?

The dev-error curve usually lies strictly above the training-error curve.

The algorithm usually has lower error on the _____ set.

Match each element of the error plot to its usual interpretation.

Order the reasoning that predicts the usual positions of the two error curves.

Explain why the dev-error curve is usually above the training-error curve.

Diagnose a plot where the red dev-error curve stays above the blue training-error curve.

What does a dev-error curve above the training-error curve indicate?

How should the two curves usually be positioned when blue denotes training error and red denotes dev error?

A plot with training error strictly above dev error displays the usual relationship.