For authors

Call for papers Submission instructions Call for open problems

Call for papers

The 32nd Annual Conference on Learning Theory (COLT 2019) will take place in Phoenix, Arizona, June 25-28, 2019, as part of the ACM Federated Computing Research Conference, which also includes EC and STOC. 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
- Unsupervised and semi-supervised learning
- Interactive learning, planning and control, and reinforcement learning
- Online learning and decision-making under uncertainty
- Interactions of learning theory with other mathematical fields
- Artificial neural networks, including deep learning
- High-dimensional and non-parametric statistics
- Learning with algebraic or combinatorial structure
- Bayesian methods in learning
- Game theory and learning
- Learning with system constraints (e.g., privacy, computational, 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, the authors may support their analysis by including relevant experimental results.
All accepted papers will be presented in a single track at the conference. At least one of each paper’s authors should be present at the conference to present the work. Accepted papers will be published electronically in the Proceedings of Machine Learning Research (PMLR). The authors of accepted papers will have the option of opting-out of the proceedings in favor of a 1-page extended abstract. The full paper reviewed for COLT will then be placed on the arXiv repository.

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:

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, with the sole exception described below. The same policy applies to journals, unless the submission 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.
In coordination with the STOC 2019 PC chair, we allow papers submitted to STOC to be simultaneously submitted to COLT provided that the authors (1) explicitly state that the submission is under consideration for STOC, (2) immediately withdraw the COLT submission if the STOC submission is accepted, and (3) agree to allow the (anonymized) STOC reviews to be provided to the COLT reviewers once they are available. The authors will be allowed to submit a rebuttal to the STOC reviews a few days after the STOC reviews are available (via the submission server).

Formatting:

Submissions are limited to 12 PMLR-formatted pages, plus unlimited additional pages for references and appendices. All details, proofs and derivations required to substantiate the results must be included in the submission, possibly in the appendices. However, the contribution, novelty and significance of submissions will be judged primarily based on the main text (without appendices), and so enough details, including proof details, must be provided in the main text to convince the reviewers of the submissions’ merits. Formatting and submission instructions can be found on the conference website: http://learningtheory.org/colt2019/.

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 the opportunity to provide a short response on the PC’s initial evaluation.

Important Dates:

All dates are in 2019.
- Paper submission deadline: February 1, 11:00 PM EST
- Author feedback: March 22-27
- Author notification: April 17
- Conference: June 25-28 (welcome reception on June 24)

Submission Instructions

Formatting and anonymization

Submissions are limited to 12 single-column JMLR-formatted pages, plus additional pages for references and appendices.
Please use the following: LaTeX style files and template.
COLT reviewing is not double-blind, and program committee members will have access to author identities. It is expressly allowed to make available online a non-anonymized version of the submission or any other material that might reveal the author identities (e.g., on an author’s web page, on arXiv). However, in order to aid in minimizing the effect of initial impressions based on author identity, and in order to allow program committee members to seek double-blind reviews from sub-referees, submissions should NOT include author names or other identifying information.
  • Use the “[anon]” option in the LaTeX template to suppress author names from appearing in the submission.
  • To the extent possible, avoid including directly identifying information in the text. You should still include all relevant references, discussion, and scientific content, even if this might provide significant hints as to the author identity. But you should generally refer to your own prior work in third person.
  • Do not include acknowledgments in the submission. They can be added in the camera-ready version of accepted papers.

Submitting your paper

We will begin accepting submissions via OpenReview on January 11, 2019. Please note that, unlike at some of the other conferences that have used OpenReview, neither submissions nor the reviewing process will be public
The deadline for submissions is 11:00 PM EST on February 1, 2019.
Please contact the COLT program chairs at [email protected] if you have any questions about the policy or technical issues with the submission process.
We looking forward to reading your submissions!

Call for open problems

The Conference on Learning Theory (COLT) 2019 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 Friday May 10 at 5pm PST. 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. You should be able to clearly express the problem in a short presentation. A monetary reward, or non-monetary but fun prize, reward is a great way to stimulate interest in solving the open problem. If you would like to submit a problem, please email it to Jake Abernethy by May 10, 2019, with the subject line “COLT 2019 Open Problem Submission”. Submissions should be at most 4 pages long and should be in the COLT 2019 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 May 24, 2019. For questions please contact the COLT 2019 open problems chair, Jake Abernethy at [email protected].