COLT 2018 : Conference on Learning Theory
Call For Papers
The 31st Annual Conference on Learning Theory (COLT 2018) will take place in Stockholm, Sweden, on July 5-9, 2018 (with a welcome reception on the 4th), immediately before ICML 2018, which takes place in the same city. 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, semi-supervised, online and active learning
-Interactions with other mathematical fields
-Interactions with statistical physics
-Artificial neural networks, including deep learning
-High-dimensional and non-parametric statistics
-Learning with algebraic or combinatorial structure
-Geometric and topological data analysis
-Bayesian methods in learning
-Planning and control, including reinforcement learning
-Learning with system constraints: e.g. privacy, memory or communication budget
-Learning from complex data: e.g., networks, time series, etc.
-Learning in other settings: e.g. social, economic, and game-theoretic
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.
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.
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 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 either through the Easychair submission form, or via email to the program chairs.
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 here.
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.
-Paper submission deadline: February 16, 2018, 11:00 PM EST
-Author feedback: April 18-21, 2018
-Author notification: May 2, 2018
-Conference: July 5-9, 2017 (welcome reception on the 4th)
Papers should be submitted through EasyChair at https://easychair.org/conferences/?conf=colt2018
Sebastien Bubeck (Microsoft Research)
Philippe Rigollet (MIT)