http://learningtheory.org/colt2006/cfp/index.html 数据挖掘研究院
The 19th Annual COLT (Conference on Learning Theory, formerly Workshop on Computational Learning Theory) will be held in Pittsburgh, Pennsylvania, USA, June 22-25, 2006.
We invite submissions of papers addressing the theoretical modeling and analysis of all aspects of learning and empirical inference. We strongly support a broad definition of learning theory, including:
- Analysis of learning algorithms and their generalization ability
- Computational complexity of learning
- Bayesian analysis
- Statistical mechanics of learning systems
- Optimization procedures for learning
- Inductive inference
- Boolean function learning
- Inductive logic programming
- Unsupervised and semi-supervised learning
- On-line learning and relative loss bounds
- Learning in planning and control (including reinforcement learning)
- Mathematical analysis of learning in related fields (e.g. game theory, neuroscience)
We welcome theoretical papers about learning that do not fit into the above categories. We are particularly interested in papers that include viewpoints that are new to the COLT community. While the primary focus of the conference is theoretical, papers can be strengthened by the inclusion of relevant experimental results. We also welcome experimental and algorithmic papers provided they are relevant to the focus of the conference by elucidating theoretical results in learning. 数据挖掘实验室
All papers will appear in the proceedings, to be published in the Springer Lecture Notes in Artificial Intelligence series. The proceedings will appear both as a printed book and in a full-text electronic version, thus we require electronic submissions. Papers that have previously appeared in journals or at other conferences, or that are being submitted to other conferences are not appropriate for COLT. 数据挖掘研究院
Paper format
Submissions should include the title, authors′ names, postal and email addresses, and a 200-word summary of the paper suitable for the conference program. They should be no longer than 15 pages using the Springer LNCS style file (see http://www.springer.de/comp/lncs/authors.html). Your paper should include a clear definition of the theoretical model used and a clear description of the results, as well as a discussion of their significance, including comparison to other work. Submit papers electronically in pdf or ps format (for details see conference website). 数据挖掘研究院
While it is not expected that all full proofs can be included in the paper, authors should strive to at least present partial proofs which will enable the reviewers to understand the main ideas and methods used. The paper should also attempt to be as self-contained as possible. 数据挖掘研究院
Open problems session
We also invite submission of open problems (see separate call). These should be constrained to two pages using the same formatting as for the full papers. There is a shorter reviewing period for the open problems. Accepted contributions will be allocated short presentation slots in a special open problems session and will be allowed two pages each in the proceedings. 数据挖掘研究院
Mark Fulk Award
This award is for the best paper authored or coauthored by a student. Eligible authors who wish to be considered for this prize should indicate this on their submission′s title page. 数据挖掘研究院
More information
Electronic submission instructions will become available in early December.
Please note the CONFLICT between submissions to STOC 2006 (Notification: January 31) and submissions to COLT 2006 (Submission deadline: January 21).
The members of the program comittee can be found under Organization. For more Information about the local organization see the general information page.
