Call for Papers

The 33rd Annual Conference on Learning Theory (COLT 2020) will take place in Graz, Austria during July 9-12, 2020. We invite submissions of papers addressing theoretical aspects of machine learning and related topics. We strongly support a broad definition of learning theory, including, but not limited to:

  • Design and analysis of learning algorithms
  • Statistical and computational complexity of learning
  • Optimization methods for learning, and/or online and/or stochastic optimization
  • Supervised learning
  • Unsupervised and semi-supervised learning
  • Active and interactive learning
  • Reinforcement learning
  • Online learning and decision-making
  • Interactions of learning theory with other mathematical fields
  • Theory of artificial neural networks, including (theory of) deep learning
  • High-dimensional and non-parametric statistics
  • Learning with algebraic or combinatorial structure
  • Theoretical analysis of probabilistic graphical models
  • Bayesian methods in learning
  • Game theory and learning
  • Learning with system constraints (e.g., privacy, fairness, memory, communication)
  • Learning from complex data (e.g., networks, time series)
  • Learning in other settings (e.g., computational social science, economics)

Submissions by authors who are new to COLT are encouraged. While the primary focus of the conference is theoretical, authors may support their analysis by including relevant experimental results.

All accepted papers will be presented at the conference as both oral talks and in a poster session. At least one author of each accepted paper should be present at the conference to present the work. Accepted papers will be published electronically in the Proceedings of Machine Learning Research (PMLR). Authors of accepted papers will have the option of opting out of the proceedings in favor of a 1-page extended abstract, which will point to an open access archival version of the full paper reviewed for COLT.

PAPER AWARDS

COLT will award both best paper and best student paper awards. To be eligible for the best student paper award, the primary contributor(s) must be full-time students at the time of submission. For eligible papers, authors must indicate at submission time if they wish their paper to be considered for a student paper award. The program committee may decline to make these awards, or may split them among several papers.

DUAL SUBMISSIONS POLICY

Conferences: In general, submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to other peer-reviewed conferences with proceedings may not be submitted to COLT. The only exception is for papers under submission to STOC 2020, as detailed below.

Dual submission with STOC 2020: The STOC 2020 notification date falls 9 days after the COLT 2020 submission deadline. In coordination with the STOC 2020 program chair, we will allow submissions that are substantially similar to papers that have been submitted to STOC 2020, provided that the authors (1) declare such dual submissions through the submission server, and (2) immediately withdraw the COLT submission if the STOC submission is accepted.

Journals: As with conferences, in general, submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to journals may not be submitted to COLT. The only exception is when the submission to COLT is a short version of a paper submitted to a journal, and not yet published. Authors must declare such dual submissions through the submission server.

SUBMISSION INSTRUCTIONS

See Submission Instructions page.

REBUTTAL PHASE

As in previous years, there will be a rebuttal phase during the review process. Initial reviews will be sent to authors before final decisions have been made. Authors will have an opportunity to provide a short response to the initial reviews.

IMPORTANT DATES

(All dates are in 2020.)

  • Paper submission deadline: January 31, 4:00 PM PST
  • Author feedback: March 28 - April 3
  • Author notification: May 1
  • Conference: July 9-12

Call for Open Problems

The Conference on Learning Theory (COLT) 2020 will include a session devoted to the presentation of open problems. A description of these problems will also appear in the COLT proceedings. The deadline for submission is May 15, end of day (PDT).

The write-up of an open problem should include:

  • A clearly defined problem
  • The motivation for studying the problem, with an argument why it is important and interesting
  • The current state of this problem, including any known partial or conjectured solutions and relevant references.

We encourage submissions of problems that have not been previously investigated theoretically, as long as there is a convincing reason to include the problem in the conference. For open problems that have already appeared in published work the submission should include enough new content to merit a separate publication. You should be able to clearly express the problem in a short presentation. A monetary reward, or non-monetary but fun prize, is a great way to stimulate interest in solving the open problem.

If you would like to submit a problem, please email it to Vitaly Feldman by May 15, 2020. Submissions should be at most 4 pages long and should be in the COLT 2020 JMLR format (found here). Submissions are non-anonymous; that is, they should contain authors' names.

Examples of open problems from past years:

Notification of acceptance or rejection will be sent out by Friday June 5, 2020.

For questions please contact the COLT 2020 open problems chair, Vitaly Feldman at [email protected].