The Seventh International Workshop on Languages for InferenceLAFI 2022
NEWS LAFI 2022 will be a purely virtual event. Detailed schedule to be posted soon.
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 statistical 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
- Applications of inference and/or differentiable programming
Sun 16 JanDisplayed time zone: Eastern Time (US & Canada) change
09:00 - 10:00 | KeynoteLAFI at LAFI Chair(s): Cameron Freer Massachusetts Institute of Technology, Ohad Kammar University of Edinburgh | ||
09:00 60mKeynote | Abstract types in probabilistic programmingRemote LAFI Sam Staton University of Oxford File Attached |
10:20 - 12:00 | |||
10:20 33mTalk | Probabilistic and Differentiable Programming in Scientific SimulatorsRemote LAFI Atılım Güneş Baydin Department of Engineering Science, University of Oxford File Attached | ||
10:53 33mTalk | Stateful processes in probabilistic programming Remote LAFI Hugo Paquet University of Cambridge File Attached | ||
11:26 33mTalk | Programming Languages for Automatic Differentiation: What Now?Remote LAFI Damiano Mazza CNRS File Attached |
13:30 - 14:45 | |||
13:30 37mTalk | JAX: accelerating ML research with composable function transformationsRemote LAFI Roy Frostig Google Research | ||
14:07 37mTalk | Scalable structure learning and inference for domain-specific probabilistic programsRemote LAFI Feras Saad Massachusetts Institute of Technology |
15:05 - 16:20 | |||
15:05 18mTalk | Towards Denotational Semantics of AD for Higher-Order, Recursive, Probabilistic LanguagesRemote LAFI Alexander K. Lew Massachusetts Institute of Technology, USA, Mathieu Huot Oxford University, Vikash K. Mansinghka MIT File Attached | ||
15:23 18mTalk | A Language and Smoothed Semantics for Convergent Stochastic Gradient DescentRemote LAFI File Attached | ||
15:42 18mTalk | Nonparametric Involutive Markov Chain Monte CarloRemote LAFI Carol Mak University of Oxford, Fabian Zaiser University of Oxford, C.-H. Luke Ong University of Oxford File Attached | ||
16:01 18mTalk | Rigorous Approximation of Posterior Inference for Probabilistic ProgramsRemote LAFI Fabian Zaiser University of Oxford, Raven Beutner CISPA Helmholtz Center for Information Security, Germany, C.-H. Luke Ong University of Oxford File Attached |
16:40 - 17:30 | KeynoteLAFI at LAFI Chair(s): Ohad Kammar University of Edinburgh, Christine Tasson Sorbonne Université — LIP6 | ||
16:40 50mKeynote | Program Analysis of Probabilistic ProgramsRemote LAFI Maria I. Gorinova The University of Edinburgh File Attached |
Call for Extended Abstracts
=====================================================================
Call for Extended Abstracts
LAFI 2022
POPL 2022 workshop on Languages for Inference
January 16, 2022
https://popl22.sigplan.org/home/lafi-2022
Submission deadline on October 20, 2021 - EXTENDED
====================================================================
***** Submission Summary *****
Deadline: October 20, 2021 (AoE) - EXTENDED Link: https://lafi22.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.
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 20, 2021 (AoE) - EXTENDED
Submission link: https://lafi22.hotcrp.com/
Anonymous 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.
Accepted Papers
Invited Speakers
- Sam Staton, University of Oxford
- Maria Gorinova, Twitter
- Feras Saad, Massachusetts Institute of Technology
- Hugo Paquet, University of Oxford
- Roy Frostig, Google Research
- Atılım Güneş Baydin, University of Oxford
- Damiano Mazza, Université Sorbonne Paris Nord