15. ALT 2004: Padova, Italy

@proceedings{DBLP:conf/alt/2004,
  editor    = {Shai Ben-David and
               John Case and
               Akira Maruoka},
  title     = {Algorithmic Learning Theory, 15th International Conference, ALT
               2004, Padova, Italy, October 2-5, 2004, Proceedings},
  booktitle = {ALT},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {3244},
  year      = {2004},
  isbn      = {3-540-23356-3},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

Invited Papers

• Ayumi Shinohara:
  String Pattern Discovery. 1-13
  
• Nicolò Cesa-Bianchi:
  Applications of Regularized Least Squares to Classification Problems. 14-18
  
• Luc De Raedt, Kristian Kersting:
  Probabilistic Inductive Logic Programming. 19-36
  
• Mikko Koivisto, Teemu Kivioja, Heikki Mannila, Pasi Rastas, Esko Ukkonen:
  Hidden Markov Modelling Techniques for Haplotype Analysis. 37-52
  
• Pedro Domingos:
  Learning, Logic, and Probability: A Unified View. 53
  

Inductive Inference

• Sanjay Jain, Efim B. Kinber:
  Learning Languages from Positive Data and Negative Counterexamples. 54-68
  
• M. R. K. Krishna Rao:
  Inductive Inference of Term Rewriting Systems from Positive Data. 69-82
  
• Eric Martin, Arun Sharma, Frank Stephan:
  On the Data Consumption Benefits of Accepting Increased Uncertainty. 83-98
  
• Steffen Lange, Sandra Zilles:
  Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space. 99-113
  

PAC Learning and Boostring

• Kohei Hatano, Osamu Watanabe:
  Learning r-of-k Functions by Boosting. 114-126
  
• Eiji Takimoto, Syuhei Koya, Akira Maruoka:
  Boosting Based on Divide and Merge. 127-141
  
• Akinobu Miyata, Jun Tarui, Etsuji Tomita:
  Learning Boolean Functions in AC⁰ on Attribute and Classification Noise. 142-155
  

Statistical Supervised Learning

• Amos Fiat, Dmitry Pechyony:
  Decision Trees: More Theoretical Justification for Practical Algorithms. 156-170
  
• Daniil Ryabko:
  Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data. 171-180
  
• Amiran Ambroladze, John Shawe-Taylor:
  Complexity of Pattern Classes and Lipschitz Property. 181-193
  

Statistical Analysis of Unlabeld Data

• Maria-Florina Balcan, Avrim Blum, Santosh Vempala:
  On Kernels, Margins, and Low-Dimensional Mappings. 194-205
  
• Kazuho Watanabe, Sumio Watanabe:
  Estimation of the Data Region Using Extreme-Value Distributions. 206-220
  
• Victor Maslov, Vladimir V. V'yugin:
  Maximum Entropy Principle in Non-ordered Setting. 221-233
  
• Marcus Hutter, Andrej Muchnik:
  Universal Convergence of Semimeasures on Individual Random Sequences. 234-248
  

Online Sequence Prediction

• Yuri Kalnishkan, Vladimir Vovk, Michael V. Vyugin:
  A Criterion for the Existence of Predictive Complexity for Binary Games. 249-263
  
• Chamy Allenberg-Neeman, Benny Neeman:
  Full Information Game with Gains and Losses. 264-278
  
• Marcus Hutter, Jan Poland:
  Prediction with Expert Advice by Following the Perturbed Leader for General Weights. 279-293
  
• Jan Poland, Marcus Hutter:
  On the Convergence Speed of MDL Predictions for Bernoulli Sequences. 294-308
  

Approximate Optimization Algorithms

• Mark Herbster:
  Relative Loss Bounds and Polynomial-Time Predictions for the k-lms-net Algorithm. 309-323
  
• Hans-Ulrich Simon:
  On the Complexity of Working Set Selection. 324-337
  
• Nikolas List:
  Convergence of a Generalized Gradient Selection Approach for the Decomposition Method. 338-349
  
• Keisuke Yamazaki, Sumio Watanabe:
  Newton Diagram and Stochastic Complexity in Mixture of Binomial Distributions. 350-364
  

Logic Based Learning

• Andrei A. Bulatov, Hubie Chen, Víctor Dalmau:
  Learnability of Relatively Quantified Generalized Formulas. 365-379
  
• Yasuhito Mukouchi, Masako Sato:
  Learning Languages Generated by Elementary Formal Systems and Its Application to SH Languages. 380-394
  
• Judy Goldsmith, Robert H. Sloan, Balázs Szörényi, György Turán:
  New Revision Algorithms. 395-409
  
• Marta Arias, Roni Khardon:
  The Subsumption Lattice and Query Learning. 410-424
  

Query and Reinforcement Learning

• Satoshi Matsumoto, Takayoshi Shoudai:
  Learning of Ordered Tree Languages with Height-Bounded Variables Using Queries. 425-439
  
• Jérôme Besombes, Jean-Yves Marion:
  Learning Tree Languages from Positive Examples and Membership Queries. 440-453
  
• Ana Iglesias, Paloma Martínez, Ricardo Aler, Fernando Fernández:
  Learning Content Sequencing in an Educational Environment According to Student Needs. 454-463
  

Tutorial Papers

• Toshiyuki Tanaka:
  Statistical Learning in Digital Wireless Communications. 464-478
  
• Yoshiyuki Kabashima, Shinsuke Uda:
  A BP-Based Algorithm for Performing Bayesian Inference in Large Perceptron-Type Networks. 479-493
  
• Manfred Opper, Ole Winther:
  Approximate Inference in Probabilistic Models. 494-504