diff --git a/docs/changelogs/v3.3.1.md b/docs/changelogs/v3.3.1.md index 9b6eed73..cc4b5017 100644 --- a/docs/changelogs/v3.3.1.md +++ b/docs/changelogs/v3.3.1.md @@ -4,6 +4,9 @@ * Support `Cautious` variant to `AdaShift` optimizer. (#310) * Save the state of the `Lookahead` optimizer too. (#310) +* Implement `APOLLO` optimizer. (#311, #312) + * [SGD-like Memory, AdamW-level Performance](https://arxiv.org/abs/2412.05270) +* Rename the `Apollo` (`An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization`) optimizer name to `ApolloDQN` not to overlap with the new optimizer name `APOLLO`. (#312) ### Bug