Skip to content
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

parmest enhancement: support params or variables #2281

Closed
adowling2 opened this issue Feb 4, 2022 · 3 comments · Fixed by #2352
Closed

parmest enhancement: support params or variables #2281

adowling2 opened this issue Feb 4, 2022 · 3 comments · Fixed by #2352

Comments

@adowling2
Copy link
Member

Summary

As part of the IDAES end-to-end uncertainty discussion, it came to light that:

  • Parameter estimation requires uncertainty model parameters to be defined as Pyomo variables
  • Robust optimization (PyROS) requires uncertain model parameters to be defined as Pyomo parameters (mutable)

Recommendation/Feature Request:

  • Generalize parmest to support either params or variables for uncertainty parameters that need to be regressed
  • PyROS already has some code to handle this conversion under the hood
  • Long-term: develop general utility code to support this conversion under the hood, we can use such a utility in parmest, PyROS, and the entire end-to-end uncertainty framework

Rationale

The distinction between variables and parameters becomes confusing to users, especially new users.

@adowling2
Copy link
Member Author

@jsiirola @kaklise This came up in a PyROS development call today. This also touches on IDAES UQ work.

@adowling2
Copy link
Member Author

Look for the expression replacement visitor in PyROS.

@adowling2
Copy link
Member Author

Leading idea: extract the conversion code from PyROS, make it into a general Pyomo utility is use across the uncertainty ecosystem

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant