-
Notifications
You must be signed in to change notification settings - Fork 86
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
Return a result even when MetricMDS does not converge #233
Comments
joeldierkes
added a commit
to joeldierkes/MultivariateStats.jl
that referenced
this issue
Sep 18, 2024
The result of a non-converged model might still be interesting. However, since `ConvergenceExceptions` are thrown these partially fitted models are discarded. This commit adds a `omit_convergence_exception` argument to all relevant functions that allows the user to omit such exceptions and return the partially trained model. The exception is still thrown in the default case to preserve backwards compatibility.
joeldierkes
added a commit
to joeldierkes/MultivariateStats.jl
that referenced
this issue
Sep 18, 2024
The result of a non-converged model might still be interesting. However, since `ConvergenceExceptions` are thrown these partially fitted models are discarded. This commit adds a `omit_convergence_exception` argument to all relevant functions that allows the user to omit such exceptions and return the partially trained model. The exception is still thrown in the default case to preserve backwards compatibility.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Three algorithms can throw a
ConvergenceException
:MetricMDS
,ICA
andPPCA
. The exception contains information about the convergence criteria and how they are unrealized, without returning an actual model.While this is the desired default behavior, it would be nice to have the option to opt out of the exception and return a model even if the convergence criteria are not met.
An application would be a repeated fit of such a model on different datasets, where the actual convergence is not as important for some individual datasets as the successful execution of the fit. The only options right now are to either exclude such a dataset or set individual convergence criteria, which is quite cumbersome.
The text was updated successfully, but these errors were encountered: