193 citations · 549 across the 24 of their papers we have counts for
Showing 2019 · cs.LGShow all
2 papers · 2 filters
cs.LG2019
Deep Double Descent: Where Bigger Models and More Data Hurt
Preetum Nakkiran, Gal Kaplun, Yamini Bansal +3
We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. More…
cs.LG2019★ 48 cited
SGD on Neural Networks Learns Functions of Increasing Complexity
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris +4
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show…