Open sondreso opened 2 months ago
This should be under Considerations:
In ERT we understand the update through the statistical properties of the ensemble X (independently sampled). We estimate Cov(X), have monte carlo samples of Y=g(X), estimate Cov(Y) and regress Y on X. The properties are understood. Changing the sampling, one risks loosing the understanding. The statistical properties, at least of these specific estimators, as a function of an LHC sample, must be understood before changing ERT.
If we use the d=1
option, the variables would still be independently sampled, or no? 🤔
If we use the
d=1
option, the variables would still be independently sampled, or no? 🤔
I think across dimensions, yes, but not across samples.
Feature Request:
Implementing stratified sampling in ERT to improve the sampling process. Stratified sampling could potentially provide a better coverage of the sample space and reduce the risk of clustering. The suggestion includes the possibility of adding a configuration option for the parameter group to define the sampling strategy, such as
RANDOM
orSTRATIFIED
, with the potential to addLATIN_HYPERCUBE
in the future.Suggested Feature
Stratified Sampling Implementation: Introduce stratified sampling as an option for parameter updates within ERT. This would involve setting
d=1
and converting to normal distribution, following the method described in this Stack Overflow post.Configuration Option: Add a new configuration option
SAMPLING_STRATEGY
on the parameter group level in the ERT configuration files. The user could specifySAMPLING_STRATEGY:STRATIFIED
to enable stratified sampling for that parameter group.Naming Consideration: Instead of naming the random sampling strategy as
RANDOM
, consider usingMONTE_CARLO
, if this is appropriate.Benefits
Considerations
STRATIFIED
the default sampling method. This is a breaking change and would require communication to users.Additional Context
UPDATE:FALSE
option was addedThis feature request has been compiled from an internal discussion (link).