Algorithmic Learning Theory: 21st International Conference, ALT 2010 Canberra, Australia, October 2010 Proceedings

ISBN-13: 9783642161070 / Angielski / Miękka / 2010 / 421 str.

Marcus Hutter; Frank Stephan; Vladimir Vovk

Opis

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 was co-located and held in parallel with Algorithmic Learning The

Spis treści

Editors’ Introduction.- Editors’ Introduction.- Invited Papers.- Towards General Algorithms for Grammatical Inference.- The Blessing and the Curse of the Multiplicative Updates.- Discovery of Abstract Concepts by a Robot.- Contrast Pattern Mining and Its Application for Building Robust Classifiers.- Optimal Online Prediction in Adversarial Environments.- Regular Contributions.- An Algorithm for Iterative Selection of Blocks of Features.- Bayesian Active Learning Using Arbitrary Binary Valued Queries.- Approximation Stability and Boosting.- A Spectral Approach for Probabilistic Grammatical Inference on Trees.- PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation.- Inferring Social Networks from Outbreaks.- Distribution-Dependent PAC-Bayes Priors.- PAC Learnability of a Concept Class under Non-atomic Measures: A Problem by Vidyasagar.- A PAC-Bayes Bound for Tailored Density Estimation.- Compressed Learning with Regular Concept.- A Lower Bound for Learning Distributions Generated by Probabilistic Automata.- Lower Bounds on Learning Random Structures with Statistical Queries.- Recursive Teaching Dimension, Learning Complexity, and Maximum Classes.- Toward a Classification of Finite Partial-Monitoring Games.- Switching Investments.- Prediction with Expert Advice under Discounted Loss.- A Regularization Approach to Metrical Task Systems.- Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations.- Learning without Coding.- Learning Figures with the Hausdorff Metric by Fractals.- Inductive Inference of Languages from Samplings.- Optimality Issues of Universal Greedy Agents with Static Priors.- Consistency of Feature Markov Processes.- Algorithms for Adversarial Bandit Problems with Multiple Plays.- Online Multiple Kernel Learning: Algorithms and Mistake Bounds.- An Identity for Kernel Ridge Regression.

O autorze

Marcus Hutter received his masters in computer sciences in 1992 at the Technical University in Munich, Germany. After his PhD in theoretical particle physics he developed algorithms in a medical software company for 5 years. For four years he has been working as a researcher at the AI institute IDSIA in Lugano, Switzerland. His current interests are centered around reinforcement learning, algorithmic information theory and statistics, universal induction schemes, adaptive control theory, and related areas.