Skip to content
This repository has been archived by the owner on Mar 8, 2023. It is now read-only.

discuss stopping criterion #5

Open
tlienart opened this issue Apr 7, 2017 · 1 comment
Open

discuss stopping criterion #5

tlienart opened this issue Apr 7, 2017 · 1 comment

Comments

@tlienart
Copy link
Collaborator

tlienart commented Apr 7, 2017

Proper stopping criterion (with theoretical guarantees) is when the clock in BPS or LBPS goes over a pre-specified (large) time T such as 1e8.

At the moment we're also stopping

  • when the number of events generated hits a pre-specified number (in LBPS)
  • when the number of gradient evaluation hits a pre-specified number (in BPS)

Both potentially add bias of some form and even though they make sense and the possibility should probably stay there, the user should be warned that the suggested choice is a maximum time.

@tlienart
Copy link
Collaborator Author

this consequently has to be sorted in src/local/simulate and src/simulate

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

No branches or pull requests

1 participant