fix: decay defaults for optimizers #492
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
polvalente
commented
Apr 26, 2023
| @@ -771,7 +771,7 @@ defmodule Axon.Updates do | |||
| Adds random Gaussian noise to the input. | |||
There was a problem hiding this comment.
The trace function in this file uses a decay-like algorithm with :decay defaulting to 0.9. Should we use this default throughout?
|
@seanmor5 Optax actually uses adamw decay ~ 0 by default, instead of ~ 1. It's best if you validate these defaults before reviewing the PR. Maybe the tests are checking agains unusual values. |
|
@polvalente if you add a test without the defaults do they pass? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes defaults for :decay option in some optimizers.
RMSProp wasn't using the option, but I'm not sure if momentum is being used correctly there