Fix multitask/added_loss_term bugs in SGPR regression #2121
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
Balandat
reviewed
Sep 7, 2022
Balandat
approved these changes
Sep 7, 2022
Agreed. We should probably add a unit test for the added loss term. |
- Enable InducingPoint kernel to work with multitask regression - Enable broadcasting for SGPR added loss term [Fixes #2113]
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Outdated suggestions cannot be applied.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.
This PR addresses two bugs
Enable InducingPoint kernel to work with multitask regression (As pointed out by @GHU2021, there's currently an error when trying to use MultitaskKernel in conjunction with InducingPointKernel)
Fix broadcasting for SGPR added loss term (Previously, the added loss term was summing over data dimensions and batch dimensions, which would artificially inflate this term for batch SGPR models. This PR ensures that we are only summing over data dimensions and not batch dimensions.)
[Fixes #2113]