Reconciling modern machine-learning practice and the classical bias–variance trade-off

On the reading lists

• #63 in Deep learning (2026 edition)

Why it matters

Formalized double descent as a framework reconciling overparameterization with strong generalization.

Condensed from the expert lists' notes.

The record

First released

2018 (from arXiv 1812.11118)

Published

2019

Citations

1,598 citations, as counted by OpenAlex (CC0)

Named by

both expert lists

Also relevant to

Machine learning foundations

Score

0.309 · computed rank 583 · consensus 0.47, must-read 0.5, citations percentile 0.337 (2010s · deep-learning), awards 0, existing lists 0. Method