Simple, Distributed, And Accelerated Probabilistic Programming

Authors:
Dustin Tran Google Brain
Matthew Hoffman Google
Dave Moore Google
Christopher Suter Google, Inc
Srinivas Vasudevan Google
Alexey Radul Google
Matthew Johnson Google Brain
Rif A. Saurous Google

Introduction:

The authors describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem.

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) with 2nd-generation tensor processing units (TPUv2s); a data-parallel autoregressive model (Image Transformer) with TPUv2s; and multi-GPU No-U-Turn Sampler (NUTS). For both a state-of-the-art VAE on 64x64 ImageNet and Image Transformer on 256x256 CelebA-HQ, our approach achieves an optimal linear speedup from 1 to 256 TPUv2 chips. With NUTS, we see a 100x speedup on GPUs over Stan and 37x over PyMC3.

You may want to know: