Deep Double Descent: Where Bigger Models and More Data Hurt

On the reading lists

• #70 in Machine learning foundations (2026 edition)

Why it matters

Demonstrated double descent across network width, training duration, and dataset size.

Condensed from the expert lists' notes.

The record

First released

2019 (from arXiv 1912.02292)

Citations

1,213 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Also relevant to

Deep learning

Score

0.278 · computed rank 660 · consensus 0.13, must-read 0.5, citations percentile 0.541 (2010s · foundations), awards 0, existing lists 0. Method