Deep Amortized Inference for Probabilistic Programs — mentioned by nextos

Tue, 14 Sep 2021 19:09:59 GMT

Apologies, for the late reply. By deep functions I simply meant small deep networks embedded in probabilistic models as a drop-in replacement for probability distributions, like e.g. a neuralHMM: https://pyro.ai/examples/hmm_funsor.html Aside from looking into Pyro docs and all references, another good entry point is this publication: https://arxiv.org/pdf/1610.05735.pdf. Here the authors show how to use deep networks to aid sampling of complex probabilistic models.

Paper and discussion history. A mention is not an endorsement.

Deep Amortized Inference for Probabilistic Programs — mentioned by fritzo

Sun, 05 Nov 2017 05:42:01 GMT

Thanks for being honest :) > ...difficulty of finding out what the actual interesting bits are. > Uber's more detailed writeup ... is vague We indeed struggled to balance accessibility and depth that blog post. One place to go deeper is the Pyro tutorials http://pyro.ai/examples For more technical framing, take a look at Noah's paper [1]. Broadly I think the "interesting bits" are the integration of newer deep neural net methods with older Bayesian methods of flexible probabilistic modeling. [1] Deep Amortized Inference for Probabilistic Programs Daniel Ritchie, Paul Horsfall, Noah D. Goodman…

Paper and discussion history. A mention is not an endorsement.

Deep Amortized Inference for Probabilistic Programs · HackerPapers discussions

Deep Amortized Inference for Probabilistic Programs — mentioned by nextos

Deep Amortized Inference for Probabilistic Programs — mentioned by fritzo