TPM2019 - Call For Papers

Call For Papers

Scope

Tractable probabilistic modeling (TPM) is concerned with the inherent trade-off between the expressivity of the probabilistic models and the complexity of performing various types of inference on them, as well as learning them from data.

Traditional topics in this area include efficient learning of probabilistic models, exact inference, and approximate routines with guarantees. Relevant model classes include low- and bounded-treewidth PGM, determinantal point processes, exchangeable probabilistic models, arithmetic circuits, sum-product networks, cutset networks, probabilistic sentential decision diagrams, and more. Successful real-world applications of such models comprise: image classification, completion and generation, scene understanding, activity recognition, language and speech modeling, bioinformatics, collaborative filtering, verification and diagnosis of physical systems.

This year's workshop will focus especially on bringing together researchers working on the different fronts and communities of TPM. We especially encourage submissions highlighting the challenges and opportunities for tractable inference and modeling within the rising field of probabilistic programming and the neural probabilistic modeling community, recently achieving impressive successes in many application fields.

Submissions can be made through the workshop page:

TPM 2019 Submissions on EasyChair

Submission Types

We invite three types of submissions:

original research papers: advances in TPM, not previously published in an archival conference or journal.
recently published research papers: advances in TPM, already published at a recent venue.
position papers: discussing tendencies, issues or future venues of interest for the TPM community.

Topics

We invite submissions about any topic pertaining tractable probabilistic modeling. Here is a non-exhaustive list of possible venues. Any other work relevant to the TPM community will be highly appreciated.

Tractable inference with neural probabilistic models
Challenges in tractable probabilistic programming
New tractable representations in discrete, continuous and hybrid domains
Tractable models and explainable AI
Learning algorithms for tractable probabilistic models
Theoretical and empirical analysis of tractable modeling
Approximate inference algorithms with guarantees on approximation quality
Applications of tractable probabilistic modeling

Important Dates

Paper submission deadline: May 10, 2019 AOE (UTC-12:00h) *
Notification to authors: May 20, 2019 *
Camera ready version: May 31, 2019 AOE (UTC-12:00h) *
Workshop Date: June 14/15, 2019 from 8:00 am to 6:00 pm *

*Authors who need to be notified sooner of acceptance, e.g. for visa or traveling purposes, are allowed to request an early review (Please notify us by email when you submit)

Submission Instructions

Submissions can be made through the workshop page:

TPM 2019 Submissions on EasyChair

Format

Recently published research papers can be submitted as they were accepted.

Original papers and abstracts are required to follow the same style guidelines of ICML 2019. Please see the LaTeX style files, and example paper. (Other software than LaTeX is not supported.)

Already accepted papers, can optionally be submitted with the original Latex style of the venue they have been accepted to.

Submitted papers can be from four up to eight pages long, not including references, and up to four extra pages when references and acknowledgments are included. Any paper exceeding this length will automatically be rejected.

Supplementary material can be put in the same pdf paper (after references); it is entirely up to the reviewers to decide whether they wish to consult this additional material.

All submissions must be electronic (through the EasyChair link above), and must closely follow the formatting guidelines in the templates; otherwise they will automatically be rejected. The author list at the submission deadline will be considered final, and no changes in authorship will be permitted for accepted papers.

Single-Blind Reviewing

Reviewing for TPM 2019 is single-blind; i.e., reviewers will know the authors’ identity but authors won't know the reviewers' identity. However, we recommend that you refer to your prior work in the third person wherever possible. We also encourage links to public repositories such as github to share code and/or data.

For any questions, please contact us at icmltpm2019@gmail.com

Google Sites

Report abuse