The 18th International Conference on Algorithmic Learning Theory (ALT 2007)
will be held in Sendai, Japan, during 1-4 October 2007.
The conference is on the theoretical
foundations of machine learning. The conference will be co-located with
the 10th International Conference on Discovery Science (DS 2007).
Topics of Interest: We invite submissions that make a wide
variety of contributions to the theory of learning, including the
Comparison of the strength of learning models and the design
and evaluation of novel algorithms for learning problems in
established learning-theoretic settings such as
the PAC model,
Analysis of the theoretical properties of existing algorithms:
- families of algorithms could include
methods for reinforcement learning or learning in repeated games,
graph- and/or manifold-based methods,
methods for latent-variable estimation and/or clustering,
methods based on Dirichlet processes,
decision tree methods,
analyses could include generalization, convergence
or computational efficiency.
Elucidation of new theoretical principles to guide the design of
learning algorithms, possibly including new
measures of algorithm quality,
general algorithm-design techniques,
Definition and analysis of new learning models. Models might
identify and formalize classes of learning problems inadequately
addressed by existing theory or
capture salient properties of important concrete applications.
The use of theory to improve the efficiency of existing principles.
Definition and analysis of models for active learning.
There will be several invited talks by prominent
researchers in the field.
Authors can submit their papers electronically via our submission page (now closed).
Files in Postscript (PS) and Portable Document Format (PDF)
- Submission deadline: 18 May 2007
(you may submit for as long as it is May 18 anywhere in the world)
Notification of acceptance or rejection will be emailed to the submitting
author by 22 June 2007
The camera-ready copy of accepted papers will be due
July 20, 2007.
Format. The submitted paper should be no
longer than 15 pages in the
for Springer-Verlag's Lecture Notes in Artificial Intelligence
series. The 15 page limit includes title, abstract, acknowledgments,
references, illustrations and any other parts of the paper; appendixes
bypassing the page limit are not allowed.
Policy. Each submitted paper will be reviewed by the members of the
program committee and be judged on clarity, significance and
Joint submissions to other conferences with published
proceedings are not allowed.
Papers that have appeared in journals or
other conferences are not appropriate for ALT 2007.
Proceedings. All accepted papers will be published as a volume
in the Lecture Notes in Artificial Intelligence, Springer-Verlag,
and will be available at the conference. Full versions of
selected papers of ALT 2007 will be invited to a special issue of the
journal Theoretical Computer Science.
E.M. Gold Award.
One scholarship of 555 € will be awarded to a
student author of an excellent paper
(please mark student submissions on the title page).
- Eiji Takimoto
- Tohoku University
- Marcus Hutter, Australian National University (Chair)
- Rocco Servedio, Columbia University (Chair)
- Marta Arias,
- Nader Bshouty,
- Sanjoy Dasgupta,
University of California, San Diego
- Claudio Gentile,
- Lisa Hellerstein,
- Sanjay Jain,
National University of Singapore
- Yuri Kalnishkan, Royal Holloway University of London
- Jyrki Kivinen, University of Helsinki
- Adam Klivans, University of Texas, Austin
- Phil Long,
- Jan Poland,
- Daniil Ryabko, IDSIA
- Frank Stephan, National University of Singapore
- Christino Tamon, Clarkson University
- Vladimir Vovk, Royal Holloway University of London
- Osamu Watanabe, Tokyo Institute of Technology
- Bob Williamson, Australian National University
Local Arrangement Chair:
- Akira Ishino
- Tohoku University