Abstract is missing.
- Editors' IntroductionJyrki Kivinen, Csaba Szepesvári, Esko Ukkonen, Thomas Zeugmann. 1-13 [doi]
- Models for Autonomously Motivated Exploration in Reinforcement Learning - (Extended Abstract)Peter Auer, Shiau Hong Lim, Chris Watkins. 14-17 [doi]
- On the Expressive Power of Deep ArchitecturesYoshua Bengio, Olivier Delalleau. 18-36 [doi]
- Optimal EstimationJorma Rissanen. 37 [doi]
- Learning from Label PreferencesEyke Hüllermeier, Johannes Fürnkranz. 38 [doi]
- Information Distance and Its ExtensionsMing Li. 39 [doi]
- Iterative Learning from Positive Data and CountersTimo Kötzing. 40-54 [doi]
- Robust Learning of Automatic Classes of LanguagesSanjay Jain, Eric Martin 0002, Frank Stephan. 55-69 [doi]
- Learning and ClassifyingSanjay Jain, Eric Martin 0002, Frank Stephan. 70-83 [doi]
- Learning Relational PatternsMichael Geilke, Sandra Zilles. 84-98 [doi]
- Adaptive and Optimal Online Linear Regression on ℓ1-BallsSébastien Gerchinovitz, Jia Yuan Yu. 99-113 [doi]
- Re-adapting the Regularization of Weights for Non-stationary RegressionNina Vaits, Koby Crammer. 114-128 [doi]
- Competing against the Best Nearest Neighbor Filter in RegressionArnak S. Dalalyan, Joseph Salmon. 129-143 [doi]
- Lipschitz Bandits without the Lipschitz ConstantSébastien Bubeck, Gilles Stoltz, Jia Yuan Yu. 144-158 [doi]
- Deviations of Stochastic Bandit RegretAntoine Salomon, Jean-Yves Audibert. 159-173 [doi]
- On Upper-Confidence Bound Policies for Switching Bandit ProblemsAurélien Garivier, Eric Moulines. 174-188 [doi]
- Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed BanditsAlexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Peter Auer. 189-203 [doi]
- The Perceptron with Dynamic MarginConstantinos Panagiotakopoulos, Petroula Tsampouka. 204-218 [doi]
- Combining Initial Segments of ListsManfred K. Warmuth, Wouter M. Koolen, David P. Helmbold. 219-233 [doi]
- Regret Minimization Algorithms for Pricing Lookback OptionsEyal Gofer, Yishay Mansour. 234-248 [doi]
- Making Online Decisions with Bounded MemoryChi-Jen Lu, Wei-Fu Lu. 249-261 [doi]
- Universal Prediction of Selected BitsTor Lattimore, Marcus Hutter, Vaibhav Gavane. 262-276 [doi]
- Semantic Communication for Simple Goals Is Equivalent to On-line LearningBrendan Juba, Santosh Vempala. 277-291 [doi]
- Accelerated Training of Max-Margin Markov Networks with KernelsXinhua Zhang, Ankan Saha, S. V. N. Vishwanathan. 292-307 [doi]
- Domain Adaptation in RegressionCorinna Cortes, Mehryar Mohri. 308-323 [doi]
- Approximate Reduction from AUC Maximization to 1-Norm Soft Margin OptimizationDaiki Suehiro, Kohei Hatano, Eiji Takimoto. 324-337 [doi]
- Axioms for Rational Reinforcement LearningPeter Sunehag, Marcus Hutter. 338-352 [doi]
- Universal Knowledge-Seeking AgentsLaurent Orseau. 353-367 [doi]
- Asymptotically Optimal AgentsTor Lattimore, Marcus Hutter. 368-382 [doi]
- Time Consistent DiscountingTor Lattimore, Marcus Hutter. 383-397 [doi]
- Distributional Learning of Simple Context-Free Tree GrammarsAnna Kasprzik, Ryo Yoshinaka. 398-412 [doi]
- On Noise-Tolerant Learning of Sparse Parities and Related ProblemsElena Grigorescu, Lev Reyzin, Santosh Vempala. 413-424 [doi]
- Supervised Learning and Co-trainingMalte Darnstädt, Hans-Ulrich Simon, Balázs Szörényi. 425-439 [doi]
- Learning a Classifier when the Labeling Is KnownShalev Ben-David, Shai Ben-David. 440-451 [doi]
- Erratum: Learning without CodingSamuel E. Moelius, Sandra Zilles. 452 [doi]