Algorithmic Learning Theory

1. Regular Contributions

   1. On-line Learning

      1. Toward a Classification of Finite Partial-Monitoring Games

         • Gábor Bartók, Dávid Pál, Csaba Szepesvári

         Pages 224-238

      2. Switching Investments

         • Wouter M. Koolen, Steven de Rooij

         Pages 239-254

      3. Prediction with Expert Advice under Discounted Loss

         • Alexey Chernov, Fedor Zhdanov

         Pages 255-269

      4. A Regularization Approach to Metrical Task Systems

         • Jacob Abernethy, Peter L. Bartlett, Niv Buchbinder, Isabelle Stanton

         Pages 270-284

   2. Inductive Inference

      1. Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations

         • John Case, Timo Kötzing

         Pages 285-299

      2. Learning without Coding

         • Samuel E. Moelius III, Sandra Zilles

         Pages 300-314

      3. Learning Figures with the Hausdorff Metric by Fractals

         • Mahito Sugiyama, Eiju Hirowatari, Hideki Tsuiki, Akihiro Yamamoto

         Pages 315-329

      4. Inductive Inference of Languages from Samplings

         • Sanjay Jain, Efim Kinber

         Pages 330-344

   3. Reinforcement Learning

      1. Optimality Issues of Universal Greedy Agents with Static Priors

         • Laurent Orseau

         Pages 345-359

      2. Consistency of Feature Markov Processes

         • Peter Sunehag, Marcus Hutter

         Pages 360-374

      3. Algorithms for Adversarial Bandit Problems with Multiple Plays

         • Taishi Uchiya, Atsuyoshi Nakamura, Mineichi Kudo

         Pages 375-389

   4. On-line Learning and Kernel Methods

      1. Online Multiple Kernel Learning: Algorithms and Mistake Bounds

         • Rong Jin, Steven C. H. Hoi, Tianbao Yang

         Pages 390-404

      2. An Identity for Kernel Ridge Regression

         • Fedor Zhdanov, Yuri Kalnishkan

         Pages 405-419

2. Back Matter

   PDF

This volume contains the papers presented at the 21st International Conf- ence on Algorithmic Learning Theory (ALT 2010), which was held in Canberra, Australia, October 6–8, 2010. The conference was co-located with the 13th - ternational Conference on Discovery Science (DS 2010) and with the Machine Learning Summer School, which was held just before ALT 2010. The tech- cal program of ALT 2010, contained 26 papers selected from 44 submissions and ?ve invited talks. The invited talks were presented in joint sessions of both conferences. ALT 2010 was dedicated to the theoretical foundations of machine learning and took place on the campus of the Australian National University, Canberra, Australia. ALT provides a forum for high-quality talks with a strong theore- cal background and scienti?c interchange in areas such as inductive inference, universal prediction, teaching models, grammatical inference, formal languages, inductive logic programming, query learning, complexity of learning, on-line learning and relative loss bounds, semi-supervised and unsupervised learning, clustering,activelearning,statisticallearning,supportvectormachines,Vapnik- Chervonenkisdimension,probablyapproximatelycorrectlearning,Bayesianand causal networks, boosting and bagging, information-based methods, minimum descriptionlength,Kolmogorovcomplexity,kernels,graphlearning,decisiontree methods, Markov decision processes, reinforcement learning, and real-world - plications of algorithmic learning theory. DS 2010 was the 13th International Conference on Discovery Science and focused on the development and analysis of methods for intelligent data an- ysis, knowledge discovery and machine learning, as well as their application to scienti?c knowledge discovery. As is the tradition, it wasco-located and held in parallel with Algorithmic Learning Theory.

• algorithmic learning theory
• algorithms
• classification
• complexity
• complexity theory
• decision trees
• grammtical inference
• inductive inference
• kolmogorov complexity
• logic programming
• query learning
• statistical learn
• support vector machines
• teaching models
• unsupervised learning
• algorithm analysis and problem complexity

• Research School of Information Sciences and Engineering, Australian National University and NICTA, Canberra, Australia

  Marcus Hutter

• Department of Mathematics, National University of Singapore, Singapore, Republic of Singapore

  Frank Stephan

• Department of Computer Science, University of London, Royal Holloway, Egham, Surrey, UK

  Vladimir Vovk

• Division of Computer Science, Hokkaido University, , ,, Japan

  Thomas Zeugmann

Policies and ethics