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 models and algorithms for learning
Unsupervised, semi-supervised, and active learning
Online learning
Artificial neural networks, including deep learning
Learning with large-scale datasets
Decision making under uncertainty
Bayesian methods in learning
High dimensional and non-parametric statistical inference
Planning and control, including reinforcement learning
Learning with additional constraints: e.g. privacy, memory or communication budget
Learning in other settings: e.g. social, economic, and game-theoretic
Analysis and applications of learning theory in related fields: natural language processing, neuroscience, bioinformatics, privacy and security, machine vision, information retrieval
Submissions by authors who are new to COLT are encouraged. While the primary focus of the conference is theoretical, the authors are encouraged to support their analysis by including relevant experimental results.

The conference will be co-located with ICML (held on June 19-24) and will feature plenary talks by David Donoho (Stanford), Ravi Kannan (Microsoft Research) and Ronitt Rubinfeld (MIT and Tel Aviv University).

All accepted papers will be presented in a single track at the conference, either as a longer (20 minutes) or a shorter (10 minute) talk. 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 JMLR Workshop and Conference Proceedings series. The authors of accepted papers will have the option of opting-out of the proceedings in favor of an extended abstract. The full paper reviewed for COLT will then be placed on the arXiv repository.

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 (using a footnote on the first page of the paper) 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.

Submissions that are substantially similar to versions that have been previously published, accepted for publication, or submitted in parallel to other conferences may not be submitted to COLT. For further details regarding the policy of dual submissions, consult the website.

There is no page limit for the submission. However, the submission should contain, within its first 12 (or fewer) pages, a concise and clear presentation of the paper’s contributions, including prior work and key technical ideas and methods used to achieve the main claims. The submission should also allow reviewers to easily expand their understanding of any of the specifics to the extent they deem important to the evaluation of the submission. In particular, submissions should include all of the ideas necessary for an expert to fully verify the central claims in the paper. Further formatting and submission instructions can be found here.

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.

Open Problems Session: We also invite submission of open problems. A separate call for open problems will be made available on the conference website.

Important Dates:

Paper submission deadline: February 12, 2016, 11:00 PM EST
Author feedback: April 1-7, 2016
Author notification: April 25, 2016
Conference: June 23-26, 2016