NeurIPS 2019 Workshop on Information Theory and Machine Learning

Abstract

Information theory is deeply connected to two key tasks in machine learning: prediction and representation learning. Due to these connections, information theory has found wide applications in machine learning, such as proving generalization bounds, certifying fairness and privacy, optimizing information content of unsupervised/supervised representations, and proving limitations to prediction performance. Conversely, progress in machine learning has driven advancements in classical information theory problems such as compression and transmission.

This workshop aims to bring together researchers from different disciplines, identify common grounds, and spur discussion on how information theory can apply to and benefit from modern machine learning tools. Topics include, but are not limited to:

  • Controlling information quantities for performance guarantees, such as PAC-Bayes, interactive data analysis, information bottleneck, fairness, privacy. Information theoretic performance limitations of learning algorithms.
  • Information theory for representation learning and unsupervised learning, such as its applications to generative models, learning latent representations, and domain adaptation.
  • Methods to estimate information theoretic quantities for high dimensional observations, such as variational methods and sampling methods.
  • Quantification of usable / useful information, e.g. the information an algorithm can use for prediction.
  • Machine learning applied to information theory, such as designing better error-correcting codes, and compression optimized for human perception.

Call for Papers

Submit at this site: https://cmt3.research.microsoft.com/ITML2019

We invite submissions in any of the following areas:

  • Controlling information quantities for performance guarantees, such as PAC-Bayes, interactive data analysis, information bottleneck, fairness, and privacy. Information theoretic limitations / performance upper bounds of learning algorithms.
  • Information theory for representation learning, semi-supervised learning and unsupervised learning, such as its applications to generative models
  • Methods to estimate information theoretic quantities for high dimensional observations, such as variational methods, sampling methods
  • Quantification of usable / useful information, e.g. information an algorithm can use for prediction.
  • Machine learning applied to information theory, such as designing better codes, compression optimized for human perception.
  • Any other topics related to information theory and machine learning

A submission should take the form of an extended abstract (3 pages long) in PDF format using the NeurIPS style. Author names do not need to be anonymised and references may extend as far as needed beyond the 3 page upper limit. Submissions may extend beyond the 3 pages upper limit, but reviewers are not expected to read beyond the first 3 pages. Submissions that are not in NeurIPS style will be desk rejected without notice.

If research has previously appeared in a journal, workshop, or conference (including NeurIPS 2019 conference), the workshop submission should extend that previous work. Parallel submissions (such as to ICLR) are permitted.

Submissions will be accepted as contributed talks or poster presentations. Final versions will be posted on the workshop website (and are archival but do not constitute a proceedings). We will do our best to guarantee workshop registration for all accepted workshop submissions.

Key Dates

  • Submission starts: August 15, 2019
  • Extended abstract submission deadline: September 15, 2019 (23:59 AOE)
  • Acceptance notification: September 30, 2019 (23:59 AOE)
  • Camera ready submission: November 15, 2019
  • Workshop date: December 13, 2018

Speakers

Organizers

Camera Ready Instructions

Use the following modified NeurIPS style file, or include "Workshop on Information Theory and Machine Learning, " in front of the first page footnote.

https://drive.google.com/file/d/1--3XrNVcDzYXnK2hB8mPJLkJtn-PsDz7/view?usp=sharing

Use \usepackage[final]{itml2019} to include the style file.

Submit the camera ready version to CMT, with file name changed to [cmt paper submission id].pdf

Presentation Instructions

Posters should be no larger than 36W x 48H inches or 90 x 122 cm, and printed on light weight, not laminated paper. Tapes will be provided.

All accepted papers will receive a 1 minute spotlight presentation at the beginning of the poster session. Please send a one page slide in PDF format to kechoi@cs.stanford.edu no later than Dec 8th.