optimizers · google

Adagrad

Per-parameter adaptive learning rates via accumulated squared gradients (Duchi et al., 2011). Foundation for Adam/Adafactor lineage.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Weight file SHA-256	a26c7d70db24d755ed0783b7b442b0c062661778673f2490c0986c6de506a747

Re-check this yourself → Source → Full record →

What is recorded

Publisher	google
Origin	United States
Licence	BSD-3-Clause
Pulls recorded here	61,202

Elsewhere in the registry

All optimizers → Browse with filters → What will run on my hardware? →

Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.