Deep Learning Reading Group

(Theory) A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning (https://arxiv.org/abs/2310.18988):

• The conventional statistical wisdom of the bias—variance tradeoff is broken in the deep learning regime, where the “bigger is better” rule of thumb reigns supreme. One theoretical explanation for these heuristics is the double descent phenomenon. This paper provides a recent nuanced take on the nature of the phenomenon and how to approach deep learning theory from the statistical point of view.

Upcoming material is to be read before each session, so that it may be discussed in an open format. Staff and students from all backgrounds who are interested in these topics are welcome. If you are interested but haven't been to a session yet, come along. There is no need to have participated in all sessions.