-
Notifications
You must be signed in to change notification settings - Fork 7
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
FAVI vs NPE vs NSBI... #4
Comments
@jacksonloper I feel you and second that plea for a unified taxonomy. To make things worse, "neural posterior estimation" is often used for "neural posterior estimation with normalizing flows" because this generative model class happened to be one of the first to gain widespread traction. I personally try to disentangle as follows:
I would love to hear your thoughts on this, and also on ideas how we can expedite the process of the field converging to some sensible taxonomy. Cheers, |
Two things.
First thing: a suggestion to mention in the intro some of the other myriad names that point to nearly-identical ideas to neural SBI, such as NPE (neural posterior estimation) and FAVI (forward amortized variational inference) and perhaps oldest of all, sleep training (from the wake-sleep algorithm).
Second thing: is a plea for help. Is there any hope that the field will converge on one name for this? I'm personally quite fond of neural simulation based-inference, but currently in google scholar NPE gets about 452 papers whereas NSBI gets only 111. Do you have any clarity on this matter?
Many thanks!
Jackson
The text was updated successfully, but these errors were encountered: