-
-
Notifications
You must be signed in to change notification settings - Fork 1k
Model ranch
ngoodman edited this page Aug 15, 2017
·
22 revisions
On this page we are collecting all the models we might want to use as "anchor models" for the first Pyro release -- that is, models / examples that must perform well before we are happy to release.
Some concepts / components to cover with the examples:
- Recognition models
- Local per data point (mean-field) params
- Reparam Elbo estimator
- Discrete variables and their estimators
- IID and time-series
- Non-elbo objectives
Put any model / example that might be an anchor candidate here. We'll sort them out below.
Ideally each example is a model with a target data set and a reference result from a paper.
- VAE
- Classifier
- Semi-supervised classifier
- Some mixture models (which?)
- A model with stochastic recursion (AIR? Grammar?)
- An inverse simulation model?
- LDA?
- DMM?
- VRNN / RVAE?
- Something on imagenet (to verify scaling)
(What models are used as demos in our favorite VI papers? In edward?)