Algorithm Search⌘K

Conceptresearch

Double descent

Also called model-wise double descent.

Test error can fall, rise and fall again as model size or training time grows past the interpolation threshold.

Test error can fall, rise and fall again as model size or training time grows past the interpolation threshold.

About this page

The build computes these levels from the evidence in the repository. Each row says what the next level needs. Read what the levels mean.

LadderLevelWhat the next level needs
Human proofH0 no proof
  • add a proof in proofs/ (06.5)
LeanL0 no Lean part
  • name a Lean module in the lean field (07)
VisualV0 none
  • add viz/scene.ts or a figure (10)
WritingW0 stub
  • one source with a locator