Algorithmic Learning Theory

1. Front Matter

   PDF

2. Editors’ Introduction

   1. Editors’ Introduction

      • Marcus Hutter, Rocco A. Servedio, Eiji Takimoto

      Pages 1-8

3. Invited Papers

   1. A Theory of Similarity Functions for Learning and Clustering

      • Avrim Blum

      Pages 9-9

   2. Machine Learning in Ecosystem Informatics

      • Thomas G. Dietterich

      Pages 10-11

   3. Challenge for Info-plosion

      • Masaru Kitsuregawa

      Pages 12-12

   4. A Hilbert Space Embedding for Distributions

      • Alex Smola, Arthur Gretton, Le Song, Bernhard Schölkopf

      Pages 13-31

   5. Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity and Creativity

      • Jürgen Schmidhuber

      Pages 32-33

4. Invited Papers

   1. Inductive Inference

      1. Feasible Iteration of Feasible Learning Functionals

         • John Case, Timo Kötzing, Todd Paddock

         Pages 34-48

      2. Parallelism Increases Iterative Learning Power

         • John Case, Samuel E. Moelius III

         Pages 49-63

      3. Prescribed Learning of R.E. Classes

         • Sanjay Jain, Frank Stephan, Nan Ye

         Pages 64-78

      4. Learning in Friedberg Numberings

         • Sanjay Jain, Frank Stephan

         Pages 79-93

5. Complexity Aspects of Learning

   1. Separating Models of Learning with Faulty Teachers

      • Vitaly Feldman, Shrenik Shah, Neal Wadhwa

      Pages 94-106

   2. Vapnik-Chervonenkis Dimension of Parallel Arithmetic Computations

      • César L. Alonso, José Luis Montaña

      Pages 107-119

   3. Parameterized Learnability of k-Juntas and Related Problems

      • Vikraman Arvind, Johannes Köbler, Wolfgang Lindner

      Pages 120-134

   4. On Universal Transfer Learning

      • M. M. Hassan Mahmud

      Pages 135-149

6. Online Learning

   1. Tuning Bandit Algorithms in Stochastic Environments

      • Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári

      Pages 150-165

   2. Following the Perturbed Leader to Gamble at Multi-armed Bandits

      • Jussi Kujala, Tapio Elomaa

      Pages 166-180

   3. Online Regression Competitive with Changing Predictors

      • Steven Busuttil, Yuri Kalnishkan

      Pages 181-195

7. Unsupervised Learning

   1. Cluster Identification in Nearest-Neighbor Graphs

      • Markus Maier, Matthias Hein, Ulrike von Luxburg

      Pages 196-210

   2. Multiple Pass Streaming Algorithms for Learning Mixtures of Distributions in \({\mathbb R}^d\)

      • Kevin L. Chang

      Pages 211-226

This volume contains the papers presented at the 18th International Conf- ence on Algorithmic Learning Theory (ALT 2007), which was held in Sendai (Japan) during October 1–4, 2007. The main objective of the conference was to provide an interdisciplinary forum for high-quality talks with a strong theore- cal background and scienti?c interchange in areas such as query models, on-line learning, inductive inference, algorithmic forecasting, boosting, support vector machines, kernel methods, complexity and learning, reinforcement learning, - supervised learning and grammatical inference. The conference was co-located with the Tenth International Conference on Discovery Science (DS 2007). This volume includes 25 technical contributions that were selected from 50 submissions by the ProgramCommittee. It also contains descriptions of the ?ve invited talks of ALT and DS; longer versions of the DS papers are available in the proceedings of DS 2007. These invited talks were presented to the audience of both conferences in joint sessions.

• Boosting
• Support Vector Machine
• algorithmic learning theory
• algorithms
• complexity
• kernel method
• learning
• learning theory
• machine learning
• reinforcement learning
• supervised learning
• unsupervised learning

• RSISE @ ANU and SML @ NICTA, Canberra,, Australia

  Marcus Hutter

• Columbia University, New York, USA

  Rocco A. Servedio

• Graduate School of Information Sciences, Tohoku University,, Japan

  Eiji Takimoto

Policies and ethics