Write a Blog >>
POPL 2021
Sun 17 - Fri 22 January 2021 Online
Fri 22 Jan 2021 16:35 - 16:45 at POPL-A - Probabilistic Programming

Abstract Probabilistic programming languages allow programmers to write down conditional probability distributions that represent statistical and machine learning models as programs that use observe statements. These programs are run by accumulating likelihood at each observe statement, and using the likelihood to steer random choices and weigh results with inference algorithms such as importance sampling or MCMC. We argue that naive likelihood accumulation does not give desirable semantics and leads to paradoxes when an observe statement is used to condition on a measure-zero event, particularly when the observe statement is executed conditionally on random data. We show that the paradoxes disappear if we explicitly model measure-zero events as a limit of positive measure events, and that we can execute these type of probabilistic programs by accumulating infinitesimal probabilities rather than probability densities. We believe that our extension improves probabilistic programming languages as an executable notation for probability distributions by making it more well-behaved and more expressive, at the cost of the programmer having to be explicit about which limit is intended when conditioning on an event of measure zero.

Fri 22 Jan

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

15:45 - 16:45
Probabilistic ProgrammingPOPL at POPL-A
15:45
10m
Talk
λS: Computable Semantics for Differentiable Programming with Higher-Order Functions and Datatypes
POPL
Benjamin Sherman Massachusetts Institute of Technology, USA, Jesse Michel Massachusetts Institute of Technology, Michael Carbin Massachusetts Institute of Technology
Link to publication DOI
15:55
10m
Talk
Deciding Accuracy of Differential Privacy Schemes
POPL
Gilles Barthe MPI-SP, Germany / IMDEA Software Institute, Spain, Rohit Chadha University of Missouri, Paul Krogmeier University of Illinois at Urbana-Champaign, A. Prasad Sistla University of Illinois at Chicago, Mahesh Viswanathan University of Illinois at Urbana-Champaign
Link to publication DOI
16:05
10m
Talk
Probabilistic Programming Semantics for Name Generation
POPL
Marcin Sabok McGill University, Sam Staton University of Oxford, Dario Stein University of Oxford, Michael Wolman McGill University
Link to publication DOI Pre-print
16:15
10m
Talk
Simplifying Multiple-Statement Reductions with the Polyhedral Model
POPL
Cambridge Yang MIT CSAIL, Eric Atkinson MIT CSAIL, Michael Carbin Massachusetts Institute of Technology
Link to publication DOI
16:25
10m
Talk
A Pre-Expectation Calculus for Probabilistic SensitivityDistinguished Paper
POPL
Alejandro Aguirre IMDEA Software Institute and T.U. of Madrid (UPM), Gilles Barthe MPI-SP, Germany / IMDEA Software Institute, Spain, Justin Hsu University of Wisconsin-Madison, USA, Benjamin Lucien Kaminski RWTH Aachen University, Germany, Joost-Pieter Katoen RWTH Aachen University, Christoph Matheja ETH Zurich
Link to publication DOI
16:35
10m
Talk
Paradoxes of probabilistic programming
POPL
Jules Jacobs Radboud University Nijmegen
Link to publication DOI Pre-print