fix use of decays #303
Merged
fix use of decays #303
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
This was referenced Jun 10, 2021
Merged
bors bot
added a commit
to FluxML/Flux.jl
that referenced
this pull request
Jun 10, 2021
1612: fix AdamW and improve decays docs r=DhairyaLGandhi a=CarloLucibello There is great disorder under the sky with optimizers. Since in chaining optimizers ``` opt = Optimizer(opt1, opt2) ``` the order generally matters (a lot!) we have to be very careful in documenting how to use decays. In fact, we were giving completely wrong indirections for `InvDecays` and `ExpDecays`. The correct ordering for standard use is ```julia Optimizer(WeightDecay(), ADAM()) # equivalent to L2 regularization Optimizer(ADAM(), InvDecay()) # learning rate scheduling Optimizer(ADAM(), ExpDecay()) # learning rate scheduling ``` Different orderings are to be typically considered as bugs in user code. This PR fixes examples and tries to clarify documentation in this regard. Also fixes AdamW, which was doing something totally wrong due to the aforementioned confusion. (see https://towardsdatascience.com/why-adamw-matters-736223f31b5d for how AdamW works). Related in model-zoo: FluxML/model-zoo#303 and FluxML/model-zoo#304 Co-authored-by: CarloLucibello <carlo.lucibello@gmail.com> Co-authored-by: Carlo Lucibello <carlo.lucibello@unibocconi.it>
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Outdated suggestions cannot be applied.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.
WeightDecayand similia should always be applied before the actual optimizer, otherwise their contribution to the gradient won't be multiplied by the learning rate.cc @carlobaldassi