Write a Blog >>
POPL 2021
Sun 17 - Fri 22 January 2021 Online

Inference concerns re-calibrating program parameters based on observed data, and has gained wide traction in machine learning and data science. Inference can be driven by probabilistic analysis and simulation, and through back-propagation and differentiation. Languages for inference offer built-in support for expressing probabilistic models and inference methods as programs, to ease reasoning, use, and reuse. The recent rise of practical implementations as well as research activity in inference-based programming has renewed the need for semantics to help us share insights and innovations.

This workshop aims to bring programming-language and machine-learning researchers together to advance all aspects of languages for inference. Topics include but are not limited to:

design of programming languages for inference and/or differentiable programming; inference algorithms for probabilistic programming languages, including ones that incorporate automatic differentiation; automatic differentiation algorithms for differentiable programming languages; probabilistic generative modelling and inference; variational and differential modelling and inference; semantics (axiomatic, operational, denotational, games, etc) and types for inference and/or differentiable programming; efficient and correct implementation; and last but not least, applications of inference and/or differentiable programming.

Plenary
You're viewing the program in a time zone which is different from your device's time zone change time zone

Sun 17 Jan

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

15:30 - 16:00
15:30
30m
Social Event
Sunday Breakfast Tables
Workshops and Co-located Events

16:00 - 16:50
Invited talk: Vikash K. MansinghkaLAFI at LAFI
Chair(s): Jean-Baptiste Tristan Boston College
16:50 - 17:30
Session 1LAFI at LAFI
Chair(s): Jean-Baptiste Tristan Boston College
16:50
13m
Talk
Binary Tree Hamiltonian Monte Carlo
LAFI
Carol Mak University of Oxford, Fabian Zaiser University of Oxford, C.-H. Luke Ong University of Oxford
File Attached
17:03
13m
Talk
An algebraic theory of conditioning
LAFI
Dario Stein University of Oxford, Sam Staton University of Oxford
File Attached
17:16
13m
Talk
The Selection Monad and Decision-Making Languages
LAFI
File Attached
17:30 - 18:00
17:30
30m
Break
Sunday Coffee Break
Workshops and Co-located Events

18:00 - 19:30
Session 2LAFI at LAFI
Chair(s): Dougal Maclaurin Google Research
18:00
12m
Talk
Enzyme: High-Performance Automatic Differentiation of LLVM
LAFI
William S. Moses Massachusetts Institute of Technology, Valentin Churavy MIT CSAIL
18:12
12m
Talk
Parametric Inversion of Non-Invertible Programs
LAFI
Zenna Tavares Massachusetts Institute of Technology, Javier Burroni University of Massachusetts Amherst, Edgar Minasyan Princeton University, David Morejon Massachusetts Institute of Technology, Armando Solar-Lezama Massachusetts Institute of Technology
File Attached
18:25
12m
Talk
Bayesian Neural Ordinary Differential Equations
LAFI
Raj Dandekar MIT, Vaibhav Dixit Julia Computing, Mohamed Tarek UNSW Canberra, Australia, Aslan Garcia Valadez National Autonomous University of Mexico, Chris Rackauckas MIT
Pre-print Media Attached File Attached
18:38
12m
Talk
On the Automatic Derivation of Importance Samplers from Pairs of Probabilistic Programs
LAFI
Alexander K. Lew Massachusetts Institute of Technology, USA, Ben Sherman , Marco Cusumano-Towner MIT-CSAIL, Michael Carbin Massachusetts Institute of Technology, Vikash K. Mansinghka MIT
Media Attached
18:51
12m
Talk
Decomposing reverse-mode automatic differentiation
LAFI
Roy Frostig Google Research, Matthew J. Johnson Google Brain, Dougal Maclaurin Google Research, Adam Paszke Google Research, Alexey Radul Google Research
File Attached
19:04
12m
Talk
Genify.jl: Transforming Julia into Gen to enable programmable inference
LAFI
Tan Zhi-Xuan Massachusetts Institute of Technology, McCoy R. Becker Charles River Analytics, Vikash K. Mansinghka MIT
Media Attached File Attached
19:17
12m
Talk
Probabilistic Inference Using Generators: the Statues Algorithm
LAFI
Pierre Denis independent scholar
Link to publication DOI Pre-print Media Attached File Attached
19:30 - 20:00
19:30
30m
Social Event
Sunday Hallway Time
Workshops and Co-located Events

Call for Extended Abstracts (extended deadline)

=====================================================================

                 Call for Extended Abstracts

                          LAFI 2021
         POPL 2021 workshop on Languages for Inference 

                        January 17, 2021
          https://popl21.sigplan.org/home/lafi-2021

           Submission deadline on October 30, 2020 (extended).

====================================================================

***** Submission Summary *****

Deadline: October 30, 2020 (extended) Link: https://lafi21.hotcrp.com/ Format: extended abstract (2 pages + references)

***** Call for Extended Abstracts *****

Inference concerns re-calibrating program parameters based on observed data, and has gained wide traction in machine learning and data science. Inference can be driven by probabilistic analysis and simulation, and through back-propagation and differentiation. Languages for inference offer built-in support for expressing probabilistic models and inference methods as programs, to ease reasoning, use, and reuse. The recent rise of practical implementations as well as research activity in inference-based programming has renewed the need for semantics to help us share insights and innovations.

This workshop aims to bring programming-language and machine-learning researchers together to advance all aspects of languages for inference. Topics include but are not limited to:

  • design of programming languages for inference and/or differentiable programming;

  • inference algorithms for probabilistic programming languages, including ones that incorporate automatic differentiation;

  • automatic differentiation algorithms for differentiable programming languages;

  • probabilistic generative modeling and inference;

  • variational and differential modeling and inference;

  • semantics (axiomatic, operational, denotational, games, etc) and types for inference and/or differentiable programming;

  • efficient and correct implementation;

  • and last but not least, applications of inference and/or differentiable programming.

Two years ago, we explicitly expanded the focus of the workshop from statistical probabilistic programming to encompass differentiable programming for statistical machine learning. This change seemed well-received by the community, and we want to continue it this year in an effort to extend the strong ties between programming language-based machine learning and the POPL community.

We expect this workshop to be informal, and our goal is to foster collaboration and establish common ground. Thus, the proceedings will not be a formal or archival publication, and we expect to spend only a portion of the workshop day on traditional research talks. Nevertheless, as a concrete basis for fruitful discussions, we call for extended abstracts describing specific and ideally ongoing work on probabilistic and differential programming languages, semantics, and systems.

***** Submission guidelines *****

Submission deadline on October 30, 2020 (extended).

Submission link: https://lafi21.hotcrp.com/

Extended abstracts are up to 2 pages in PDF format, excluding references.

In line with the SIGPLAN Republication Policy, inclusion of extended abstracts in the program is not intended to preclude later formal publication.