23rd International Conference on Algorithmic Learning Theory (ALT 2012)
Important Dates:
Submission Deadline: May 17, 2012
Notification: July 8, 2012
Camera ready copy: July 20, 2012
Early registration deadline: August 30, 2012
The conference: October 29 – 31, 2012
From the call for papers:
The 23rd International Conference on Algorithmic Learning Theory (ALT 2012) will be held in Lyon, France, at Université Lumière Lyon 2, on October 29-31, 2012. The conference is on the theoretical foundations of machine learning. The conference will be co-located with the 15th International Conference on Discovery Science (DS 2012)
…
Topics of Interest: We invite submissions that make a wide
variety of contributions to the theory of learning, including the
following:
- 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- statistical learning theory,
- on-line learning,
- inductive inference,
- query models,
- unsupervised, semi-supervised and active learning.
- Analysis of the theoretical properties of existing algorithms:
- families of algorithms could include
- boosting,
- kernel-based methods, SVM,
- Bayesian networks,
- methods for reinforcement learning or learning in
repeated games, - graph- and/or manifold-based methods,
- methods for latent-variable estimation and/or clustering,
- MDL,
- decision tree methods,
- information-based methods,
- analyses could include generalization, convergence or
computational efficiency.
- families of algorithms could include
- 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.
- identify and formalize classes of learning problems
.
Curious: Do you know of any research comparing the topics of interest for a conference against the terms used in presentations for the conference?