Skip to content

Comments

Pyomo.DoE: Allow user to define experiment cost to include in the objective#3527

Closed
adowling2 wants to merge 2 commits intoPyomo:mainfrom
adowling2:pyomo-doe-extended-objective
Closed

Pyomo.DoE: Allow user to define experiment cost to include in the objective#3527
adowling2 wants to merge 2 commits intoPyomo:mainfrom
adowling2:pyomo-doe-extended-objective

Conversation

@adowling2
Copy link
Member

@adowling2 adowling2 commented Mar 20, 2025

Fixes # .

Summary/Motivation:

  • For some MBDoE problems (especially dynamic with many degrees of freedom), the FIM-based objective can be "flat", i.e., there are many different experiment designs with very similar information content
  • Thus, it is desirable for the user to be able to specify a second objective, e.g., experiment_cost, that can also be minimized

Changes proposed in this PR:

  • Extended interface to consider experiment_cost
  • Allow user to specify weight for experiment cost component of the objective

TODO Before Converting from Draft:

  • Decide if this is a good approach, or should the experiment_cost be specified with suffixes?
  • Do we want just one auxiliary objective (experiment cost) or to support many auxiliary objectives?
  • Update documentation
  • Create an example
  • Add tests
  • Add error checking
  • Run black

Legal Acknowledgement

By contributing to this software project, I have read the contribution guide and agree to the following terms and conditions for my contribution:

  1. I agree my contributions are submitted under the BSD license.
  2. I represent I am authorized to make the contributions and grant the license. If my employer has rights to intellectual property that includes these contributions, I represent that I have received permission to make contributions and grant the required license on behalf of that employer.

@adowling2 adowling2 marked this pull request as draft March 20, 2025 11:12
@adowling2
Copy link
Member Author

@adowling2 @blnicho @jsiirola Quick feedback on this concept is welcome

@djlaky
Copy link
Contributor

djlaky commented Mar 20, 2025

Use the average over the scenarios instead of only the base scenario? Central finite difference in mind with this idea.

@mrmundt
Copy link
Contributor

mrmundt commented Mar 20, 2025

Please make sure to run black -S -C with the most recent version of black on your code.

@adowling2
Copy link
Member Author

We ended up not needing this for the problem I was working on. I am closing this PR for now. But keeping it on our project board in case we want to revisit it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

Development

Successfully merging this pull request may close these issues.

4 participants