Simple, Distributed, and Accelerated Probabilistic Programming

Dave Moore
Dave Moore
Christopher Suter
Christopher Suter
Srinivas Vasudevan
Srinivas Vasudevan
Matthew Johnson
Matthew Johnson
Rif A. Saurous
Rif A. Saurous

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), pp. 7598-7609, 2018.

Cited by: 31|Bibtex|Views52|Links
EI
Keywords:
random variableprobabilistic programminglinear speedup

Abstract:

We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction-the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-parallel variational auto-encoder (vAE) wit...More

Code:

Data:

Your rating :
0

 

Tags
Comments