Tue 9 Jan 2018 10:12 - 10:15 at Bradbury - POSTER SESSION (14 posters - not talks)

The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation. Building on two basic abstractions, it offers flexible building blocks for probabilistic computation. Distributions provide fast, numerically stable methods for generating samples and computing statistics, e.g., log density. Bijectors provide composable volume-tracking transformations with automatic caching. Together these enable modular construction of high dimensional distributions and transformations not possible with previous libraries (e.g., pixelCNNs, autoregressive flows, and reversible residual networks). They are the workhorse behind deep probabilistic programming systems like Edward and empower fast black-box inference in probabilistic models built on deep-network components. TensorFlow Distributions has proven an important part of the TensorFlow toolkit within Google and in the broader deep learning community.

Tue 9 Jan

pps-2018
10:00 - 10:30: PPS 2018 - POSTER SESSION (14 posters - not talks) at Bradbury
pps-201810:00 - 10:02
Talk
Nils NappSUNY at Buffalo, Marco GaboardiUniversity at Buffalo, SUNY
pps-201810:02 - 10:04
Talk
C.-H. Luke OngUniversity of Oxford, Matthijs VákárUniversity of Oxford
pps-201810:04 - 10:06
Talk
Javier Burroni, Arjun GuhaUniversity of Massachusetts, Amherst, David JensenUniversity of Massachusetts Amherst
Pre-print
pps-201810:06 - 10:08
Talk
pps-201810:08 - 10:10
Talk
Mathias Ruggaard PedersenAalborg University, Nathanaël FijalkowAlan Turing Institute, Giorgio BacciAalborg University, Kim LarsenAalborg University, Radu MardareAalborg University
pps-201810:10 - 10:12
Talk
Avi PfefferCharles River Analytics
pps-201810:12 - 10:15
Talk
Link to publication Pre-print
pps-201810:15 - 10:17
Talk
Benjamin ShermanMassachusetts Institute of Technology, USA, Jared TramontanoMassachusetts Institute of Technology, Michael CarbinMIT
Pre-print
pps-201810:17 - 10:19
Talk
Marco Cusumano-TownerMIT-CSAIL, Vikash MansinghkaMassachusetts Institute of Technology
pps-201810:19 - 10:21
Talk
Steffen SmolkaCornell University, David KahnCornell University, Praveen KumarCornell University, Nate FosterCornell University, Dexter Kozen, Alexandra SilvaUniversity College London
Link to publication File Attached
pps-201810:21 - 10:23
Talk
Tetsuya SatoUniversity at Buffalo, SUNY, USA
pps-201810:23 - 10:25
Talk
Andres Molina-MarkhamThe MITRE Corporation
pps-201810:25 - 10:27
Talk
Avi PfefferCharles River Analytics
pps-201810:27 - 10:30
Talk
Daniel LundénKTH Royal Institute of Technology, David BromanKTH Royal Institute of Technology, Lawrence M. MurrayUppsala University