pyro-ppl / pyro

Deep universal probabilistic programming with Python and PyTorch
http://pyro.ai
Apache License 2.0
8.55k stars 987 forks source link

Add broadcasting semantics to EmpiricalMarginal and TracePosterior #825

Open eb8680 opened 6 years ago

eb8680 commented 6 years ago

Along the lines of #791, we should allow global independence dimensions in Marginal and TracePosterior.

ngoodman commented 6 years ago

great idea. (related: make importance parallel.)

this is possible only when the underlying computation is batchable. it might be sometimes hard to tell if this is so. is it possible to dynamically detect a failure of batching and bail out to the serial method?

fritzo commented 6 years ago

Search was removed in #1044 . As I understand, Search would be reimplemented as part of this issue.

fritzo commented 6 years ago

@eb8680 Does this issue also cover paralleization / batch-support for SVI? I'd like to implement batched inference to expose our EM solvers (BP + Newton).

eb8680 commented 6 years ago

Does this issue also cover paralleization / batch-support for SVI?

What did you have in mind?

fritzo commented 6 years ago

@eb8680 What did you have in mind?

I've written some details in #1213

fritzo commented 5 years ago

@eb8680 is this still on track for our 0.3 release with PyTorch 1.0?

eb8680 commented 5 years ago

is this still on track for our 0.3 release with PyTorch 1.0?

We don't have an immediate use case, so probably not