The 28th Annual Conference on Learning Theory (COLT 2015) will take place in Paris, France, on July 3-6, 2015.
We invite submissions of papers addressing theoretical aspects of machine learning and related topics. Submissions by authors who are new to COLT are encouraged. We strongly support a broad definition of learning theory, including, but not limited to:
• Design and analysis of learning algorithms and their generalization ability
• Statistical and computational complexity of learning
• Optimization models and algorithms for learning
• Unsupervised, semi-supervised learning, and clustering
• Online learning
• Deep learning and artificial neural networks
• Decision making under uncertainty
• Bayesian Theory
• Kernel Methods
• High dimensional and non-parametric empirical inference, including sparsity methods
• Planning and control, including reinforcement learning
• Learning with additional constraints: E.g. privacy, time or memory budget, communication
• 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, data mining, information retrieval.
We are also interested in papers that include viewpoints that are new to the COLT community. We welcome experimental and algorithmic papers provided they are relevant to the focus of the conference by elucidating theoretical results. Also, while the primary focus of the conference is theoretical, papers can be strengthened by the inclusion of relevant experimental results.
COLT will award both best paper and best student paper awards. Best student papers must be authored or coauthored by a student. Authors must indicate (using a footnote on the first page of the paper) at submission time if they wish their paper to be eligible for a student award. This does not preclude the paper to be eligible for the best paper award. The program committee may decline to make these awards, or may split them among several papers.
Papers that are currently under review or have already been accepted or published in a refereed venue, including conferences and journals, may not be submitted.
Accepted papers will be published electronically, in the JMLR Workshop and Conference Proceedings series. Selected papers will be invited to a special issue of JMLR and/or MLJ. The authors of accepted papers will have the option of opting-out of the proceedings in favor of a 1-page abstract. The full paper reviewed for COLT will then be placed on the ArXiV repository and linked from the conference webpage.
All accepted papers will be plenarily presented at the conference, either as a long or as a short talk. At least one of the paper’s authors should be present at the conference to present the work.
As in the previous years, we will have 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 at the conference website.
Submissions are limited to 12 JMLR-formatted pages, plus 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.
Papers should be submitted through EasyChair at
• Paper submission deadline: February 19th, 2015, 11:00 PM EST
• Author Feedback: April 10-15, 2015
• Author notification: May 1, 2015
• Conference: July 3-6, 2015