Write a Blog >>
Wed 22 Jan 2020 10:51 - 11:13 at Ile de France II (IDF II) - Probabilistic Programming Chair(s): Alexandra Silva

Modern probabilistic programming languages aim to formalize and automate key aspects of probabilistic modeling and inference. Many languages provide constructs for programmable inference that enable developers to improve inference speed and accuracy. Unfortunately, it is easy to use these constructs to write unsound programs that appear to run correctly but that produce meaningless results. This paper presents a denotational semantics for higher-order probabilistic programs with programmable inference, along with a type system that ensures that well-typed inference programs are sound by construction. A central insight is that the type of a probabilistic expression can track the space of its possible execution traces, not just the type of value that it returns, as these traces are often the objects that are manipulated during inference. We use our semantics and type system to establish soundness properties of custom inference programs that use constructs for variational, sequential Monte Carlo, importance sampling, and Markov chain Monte Carlo inference.

Wed 22 Jan
Times are displayed in time zone: (GMT-06:00) Saskatchewan, Central America change

10:30 - 11:35: Research Papers - Probabilistic Programming at Ile de France II (IDF II)
Chair(s): Alexandra SilvaUniversity College London
POPL-2020-Research-Papers10:30 - 10:51
Wonyeol LeeKAIST, Hangyeol YuKAIST, Xavier RivalINRIA/CNRS/ENS Paris, Hongseok YangKAIST
Link to publication DOI Media Attached
POPL-2020-Research-Papers10:51 - 11:13
Alexander K. LewMassachusetts Institute of Technology, USA, Marco Cusumano-TownerMIT-CSAIL, Benjamin ShermanMassachusetts Institute of Technology, USA, Michael CarbinMassachusetts Institute of Technology, Vikash MansinghkaMIT
Link to publication DOI Media Attached
POPL-2020-Research-Papers11:13 - 11:35
Fredrik DahlqvistUniversity College London, Dexter KozenCornell University
Link to publication DOI Media Attached File Attached