-
Notifications
You must be signed in to change notification settings - Fork 133
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Allow Bayesian Optimization to use Pre-trained GP ROM #2280
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changes look good, I do have one question, but probably nothing to hold up the merging process.
@@ -235,6 +236,8 @@ def initialize(self, externalSeeding=None, solutionExport=None): | |||
self.raiseAnError(RuntimeError, f'GPR ROM <target> should be obective variable: {self._objectiveVar}, ' | |||
f'Received {self._model.supervisedContainer[0].target}') | |||
|
|||
if self._resetModel: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can't find any logic in this file that would switch the default value of False
for _resetModel
to True
. Do you expect this value to change in this before this branch of code?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This variable has been defined in init method. Currently, the default is False. I define this variable to allow us to define a XML node in the input file to control it if needed. Currently, the default behavior works fine.
… in the pretrained data
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changes are good and are ready to merge.
Pull Request Description
What issue does this change request address? (Use "#" before the issue to link it, i.e., #42.)
close #2281
What are the significant changes in functionality due to this change request?
For experimental design, utilize existing dataset from experiment to guide the future exploration and exploitation will benefit optimal experimental design. This PR will allow pre-trained GP ROM to be used in the Bayesian Optimization. The pre-trained GP ROM is trained with existing experimental dataset.
For Change Control Board: Change Request Review
The following review must be completed by an authorized member of the Change Control Board.
<internalParallel>
to True.raven/tests/framework/user_guide
andraven/docs/workshop
) have been changed, the associated documentation must be reviewed and assured the text matches the example.