Double Trouble in Double Descent: Bias and Variance(s) in the Lazy RegimeDownload PDFOpen Website

2020 (modified: 03 Nov 2022)ICML 2020Readers: Everyone
Abstract: Deep neural networks can achieve remarkable generalization performances while interpolating the training data. Rather than the U-curve emblematic of the bias-variance trade-off, their test error of...
0 Replies

Loading