[1901.09491] Stiffness: A New Perspective on Generalization in Neural Networks

arxiv.org

Generalization is one of the most important goals of machine learning. Models that are overfit on training data aren't valuable in production. To help understand generalization better, researchers at Google introduce the concept of "stiffness". Similar to work on the analysis of variance, stiffness measures how gradient steps on one example impact loss on other examples.

Read more...
Linkedin

Want to receive more content like this in your inbox?