Write a Blog >>
Tue 21 Jan 2020 14:49 - 15:05 at St Claude - C

This talk introduces a Monte Carlo dynamic analysis of two probabilistic programs. The analysis estimates an upper bound on the difference in their output distributions for fixed inputs, as measured by Kullback-Leibler (KL) divergence. The analysis, Bridged Auxiliary Inference Divergence Estimator (BRAIDE), is a generalization of the Auxiliary Inference Divergence Estimator (AIDE). Unlike AIDE, BRAIDE analysis can be made more precise and efficient using knowledge of how the traces of the two programs relate, resulting in tighter bounds with less computation. We give an example of BRAIDE applied to two Gen probabilistic programs.

Conference Day
Tue 21 Jan

Displayed time zone: Saskatchewan, Central America change

14:00 - 15:05
14:00
30m
Talk
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
LAFI
Yuan ZhouUniversity of Oxford, Hongseok YangKAIST, Yee Whye TehUniversity of Oxford, Tom RainforthDepartment of Statistics, University of Oxford
14:32
15m
Talk
MetaPPL: Inference Algorithms as First-Class Generative Models
LAFI
Alexander K. LewMassachusetts Institute of Technology, USA, Benjamin ShermanMassachusetts Institute of Technology, USA, Marco Cusumano-TownerMIT-CSAIL, Austin GarrettMIT, Ben ZinbergMIT, Vikash K. MansinghkaMIT, Michael CarbinMassachusetts Institute of Technology
File Attached
14:49
16m
Talk
Monte Carlo Semantic Differencing of Probabilistic Programs
LAFI