-
Notifications
You must be signed in to change notification settings - Fork 12
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
Possible speedup of localization by looping observations #175
Comments
Let there be or If we know that which has the structure of a rank-1 update. |
Så litt på å loope over observasjoner Se for deg en situasjon der det er lite overlapp. Det blir mye lasting og skriving til disk. Eksempel: vi har |
Problemet du beskriv er ikkje gitt er eit problem, men ein trade-off mellom skriving til og frå disk vs. invertering av dense store matriser svært mange gangar. I algoritmen over har vi ein loop over observasjonar, så ein loop over realisasjonar, så ein loop over parametrar. Parametrar kan lastast i store batchar, så det bør ikkje vere eit kjempeproblem? Der er to problem eg ser som er urelaterte til det over:
|
Did a first stab at this here: https://github.com/Blunde1/iterative_ensemble_smoother/blob/es-observation-loop/docs/source/LinearRegression.py |
@Blunde1 writes:
The text was updated successfully, but these errors were encountered: