Double Descent in Risk Curves

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

A Brief Prehistory of Double Descent

In their thought-provoking paper [1], belkin et al.

Illustrate and discuss the shape of risk curves in the context of modern high-complexity learners.

These curves show the risk of a learner as a function of some (approximate) measure of its complexity.

With increasing the risk initially decreases, attains a minimum, and then increases until equals where the training data is fitted perfectly.

Authors

Marco Loog, Tom Viering, Alexander Mey, Jesse H. Krijthe, David M.J. Tax

◐ Recommended Members