Algorithmic Learning Theory

1. Front Matter

   PDF

2. Invited Papers

   1. String Pattern Discovery

      • Ayumi Shinohara

      Pages 1-13

   2. Applications of Regularized Least Squares to Classification Problems

      • Nicolò Cesa-Bianchi

      Pages 14-18

   3. Probabilistic Inductive Logic Programming

      • Luc De Raedt, Kristian Kersting

      Pages 19-36

   4. Hidden Markov Modelling Techniques for Haplotype Analysis

      • Mikko Koivisto, Teemu Kivioja, Heikki Mannila, Pasi Rastas, Esko Ukkonen

      Pages 37-52

   5. Learning, Logic, and Probability: A Unified View

      • Pedro Domingos

      Pages 53-53

3. Regular Contributions

   1. Inductive Inference

      1. Learning Languages from Positive Data and Negative Counterexamples

         • Sanjay Jain, Efim Kinber

         Pages 54-68

      2. Inductive Inference of Term Rewriting Systems from Positive Data

         • M. R. K. Krishna Rao

         Pages 69-82

      3. On the Data Consumption Benefits of Accepting Increased Uncertainty

         • Eric Martin, Arun Sharma, Frank Stephan

         Pages 83-98

      4. Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space

         • Steffen Lange, Sandra Zilles

         Pages 99-113

   2. PAC Learning and Boosting

      1. Learning <i>r</i>-of-<i>k</i> Functions by Boosting

         • Kohei Hatano, Osamu Watanabe

         Pages 114-126

      2. Boosting Based on Divide and Merge

         • Eiji Takimoto, Syuhei Koya, Akira Maruoka

         Pages 127-141

      3. Learning Boolean Functions in <i>AC</i> ⁰ on Attribute and Classification Noise

         • Akinobu Miyata, Jun Tarui, Etsuji Tomita

         Pages 142-155

   3. Statistical Supervised Learning

      1. Decision Trees: More Theoretical Justification for Practical Algorithms

         • Amos Fiat, Dmitry Pechyony

         Pages 156-170

      2. Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data

         • Daniil Ryabko

         Pages 171-180

      3. Complexity of Pattern Classes and Lipschitz Property

         • Amiran Ambroladze, John Shawe-Taylor

         Pages 181-193

   4. Statistical Analysis of Unlabeled Data

      1. On Kernels, Margins, and Low-Dimensional Mappings

         • Maria-Florina Balcan, Avrim Blum, Santosh Vempala

         Pages 194-205

      2. Estimation of the Data Region Using Extreme-Value Distributions

         • Kazuho Watanabe, Sumio Watanabe

         Pages 206-220

      3. Maximum Entropy Principle in Non-ordered Setting

         • Victor Maslov, Vladimir V’yugin

         Pages 221-233

      4. Universal Convergence of Semimeasures on Individual Random Sequences

         • Marcus Hutter, Andrej Muchnik

         Pages 234-248

Algorithmic learning theory is mathematics about computer programs which learn from experience. This involves considerable interaction between various mathematical disciplines including theory of computation, statistics, and c- binatorics. There is also considerable interaction with the practical, empirical ?elds of machine and statistical learning in which a principal aim is to predict, from past data about phenomena, useful features of future data from the same phenomena. The papers in this volume cover a broad range of topics of current research in the ?eld of algorithmic learning theory. We have divided the 29 technical, contributed papers in this volume into eight categories (corresponding to eight sessions) re?ecting this broad range. The categories featured are Inductive Inf- ence, Approximate Optimization Algorithms, Online Sequence Prediction, S- tistical Analysis of Unlabeled Data, PAC Learning & Boosting, Statistical - pervisedLearning,LogicBasedLearning,andQuery&ReinforcementLearning. Below we give a brief overview of the ?eld, placing each of these topics in the general context of the ?eld. Formal models of automated learning re?ect various facets of the wide range of activities that can be viewed as learning. A ?rst dichotomy is between viewing learning as an inde?nite process and viewing it as a ?nite activity with a de?ned termination. Inductive Inference models focus on inde?nite learning processes, requiring only eventual success of the learner to converge to a satisfactory conclusion.

• Boosting
• algorithmic learning theory
• algorithms
• learning
• learning theory
• logic
• optimization
• reinforcement learning
• supervised learning
• algorithm analysis and problem complexity

• David R. Cheriton School of Computer Science University of Waterloo,  

  Shoham Ben-David

• Department of Computer & Information Sciences, University of Delaware, Newark

  John Case

• Dept. of Information Technology and Electronics, Ishinomaki Senshu University,  

  Akira Maruoka

Policies and ethics