no code implementations • ICML 2020 • Ronen Basri, Meirav Galun, Amnon Geifman, David Jacobs, Yoni Kasten, Shira Kritchman
Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high frequency ones.
1 code implementation • NeurIPS 2019 • Ronen Basri, David Jacobs, Yoni Kasten, Shira Kritchman
We study the relationship between the frequency of a function and the speed at which a neural network learns it.