optimizers · juntang-zhuang

AdaBelief

Adapts step size by the belief in observed gradients — variance of gradient from its EMA (Zhuang et al., NeurIPS 2020).

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	5cc61c5770bfac47d30a6e5f0659eae47eb66aecb96fb4ce4ab97b4851860dd5

Re-check this yourself → Source → Full record →

What is recorded

Publisher	juntang-zhuang
Origin	United States
Licence	BSD-3-Clause
Pulls recorded here	14,502

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.