Fix/polynomial autograd post merge #3736
Open
Conversation
This file contains hidden or 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
…erting to sin(x) for consistency with the rest of the tutorial
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/tutorials/3736
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 35378eb with merge base b863c3b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
svekars
added
the
core
Contributor
|
looks good from a docs point of view, have someone approve the content. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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 suggestion in #3597
Description
After closing #3597 , it was pointed out by a community member that while the changes made sense in isolation, they broke the flow of the tutorial overall. In particular, the tutorial develops a number of examples around sin(x). So, this is mostly a one-liner to revert to sin(x) instead of exp(x).
As agreed in the discussion in #3597 , I also suggest in comments experimentation with exp(x) or other functions with faster polynomial convergence.
The learning rate had to be reduced for this by a factor 10 in order to converge with autograd.
I also fixed a trivial documentation typo.
Checklist
cc @albanD @jbschlosser