[ The Types Forum (announcements only), http://lists.seas.upenn.edu/mailman/listinfo/types-announce ]
LAFI 2019: Languages for Inference (formerly PPS) ================================================ Tuesday, 15 January 2019, Cascais/Lisbon, Portugal A workshop affiliated with POPL 2019 https://popl19.sigplan.org/track/lafi-2019 Important dates (anywhere on earth) ------------------------------------------------- LAFI submission deadline Thu 1 Nov 2018 Notification Mon 3 Dec 2018 Early Registration Deadline Thu 10 Dec 2018 Workshop Tue 15 Jan 2019 ------------------------------------------------- Submission: https://lafi19.hotcrp.com/ Registration: https://popl19.sigplan.org/attending/Registration Context ======= 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. For a sense of the talks, posters, and blogs in past years, see + PPS-2018: http://conf.researchr.org/track/POPL-2018/pps-2018 blog: http://pps2018.soic.indiana.edu/ + PPS-2017: http://conf.researchr.org/track/POPL-2017/pps-2017 blog: http://pps2017.soic.indiana.edu/) + PPS-2016: http://conf.researchr.org/track/POPL-2016/pps-2016 blog: http://pps2016.soic.indiana.edu/) This year we are explicitly expanding the focus of the workshop from statistical probabilistic programming to encompass differentiable programming for statistical machine learning. 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 programming languages, semantics, and systems. Submission guidelines ===================== Extended abstracts are up to 2 pages in PDF format, excluding references. Please submit them by November 1(AoE) using HotCRP at: https://lafi19.hotcrp.com/ In line with the SIGPLAN Republication Policy: http://www.sigplan.org/Resources/Policies/Republication/ inclusion of extended abstracts in the programme is not intended to preclude later formal publication. Programme committee: Atılım Güneş Baydin University of Oxford Department of Engineering Bart van Merriënboer University of Montreal Christine Tasson University Paris Diderot David Duvenaud University of Toronto Jeffrey Siskind (co-chair) School of Electrical and Computer Engineering, Purdue University Matthew Johnson Google Brain Ohad Kammar (co-chair) University of Oxford Department of Computer Science Praveen Narayanan Indiana University Ryan Culpepper Czech Technical University Sophia Gold Tezos Steven Holtzen University of California Los Angeles Tom Rainforth University of Oxford Department of Statistics