Ebook: Algorithmic Learning Theory: 22nd International Conference, ALT 2011, Espoo, Finland, October 5-7, 2011. Proceedings

This book constitutes the refereed proceedings of the 22nd International Conference on Algorithmic Learning Theory, ALT 2011, held in Espoo, Finland, in October 2011, co-located with the 14th International Conference on Discovery Science, DS 2011.
The 28 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from numerous submissions. The papers are divided into topical sections of papers on inductive inference, regression, bandit problems, online learning, kernel and margin-based methods, intelligent agents and other learning models.

---

This book constitutes the refereed proceedings of the 22nd International Conference on Algorithmic Learning Theory, ALT 2011, held in Espoo, Finland, in October 2011, co-located with the 14th International Conference on Discovery Science, DS 2011.
The 28 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from numerous submissions. The papers are divided into topical sections of papers on inductive inference, regression, bandit problems, online learning, kernel and margin-based methods, intelligent agents and other learning models.

---

This book constitutes the refereed proceedings of the 22nd International Conference on Algorithmic Learning Theory, ALT 2011, held in Espoo, Finland, in October 2011, co-located with the 14th International Conference on Discovery Science, DS 2011.
The 28 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from numerous submissions. The papers are divided into topical sections of papers on inductive inference, regression, bandit problems, online learning, kernel and margin-based methods, intelligent agents and other learning models.
Content:
Front Matter....Pages -
Editors’ Introduction....Pages 1-13
Models for Autonomously Motivated Exploration in Reinforcement Learning....Pages 14-17
On the Expressive Power of Deep Architectures....Pages 18-36
Optimal Estimation....Pages 37-37
Learning from Label Preferences....Pages 38-38
Information Distance and Its Extensions....Pages 39-39
Iterative Learning from Positive Data and Counters....Pages 40-54
Robust Learning of Automatic Classes of Languages....Pages 55-69
Learning and Classifying....Pages 70-83
Learning Relational Patterns....Pages 84-98
Adaptive and Optimal Online Linear Regression on ?1-Balls....Pages 99-113
Re-adapting the Regularization of Weights for Non-stationary Regression....Pages 114-128
Competing against the Best Nearest Neighbor Filter in Regression....Pages 129-143
Lipschitz Bandits without the Lipschitz Constant....Pages 144-158
Deviations of Stochastic Bandit Regret....Pages 159-173
On Upper-Confidence Bound Policies for Switching Bandit Problems....Pages 174-188
Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits....Pages 189-203
The Perceptron with Dynamic Margin....Pages 204-218
Combining Initial Segments of Lists....Pages 219-233
Regret Minimization Algorithms for Pricing Lookback Options....Pages 234-248
Making Online Decisions with Bounded Memory....Pages 249-261
Universal Prediction of Selected Bits....Pages 262-276
Semantic Communication for Simple Goals Is Equivalent to On-line Learning....Pages 277-291
Accelerated Training of Max-Margin Markov Networks with Kernels....Pages 292-307
Domain Adaptation in Regression....Pages 308-323
Approximate Reduction from AUC Maximization to 1-Norm Soft Margin Optimization....Pages 324-337
Axioms for Rational Reinforcement Learning....Pages 338-352
Universal Knowledge-Seeking Agents....Pages 353-367
Asymptotically Optimal Agents....Pages 368-382
Time Consistent Discounting....Pages 383-397
Distributional Learning of Simple Context-Free Tree Grammars....Pages 398-412
On Noise-Tolerant Learning of Sparse Parities and Related Problems....Pages 413-424
Supervised Learning and Co-training....Pages 425-439
Learning a Classifier when the Labeling Is Known....Pages 440-451
Erratum: Learning without Coding....Pages 452-452
Back Matter....Pages -

---

This book constitutes the refereed proceedings of the 22nd International Conference on Algorithmic Learning Theory, ALT 2011, held in Espoo, Finland, in October 2011, co-located with the 14th International Conference on Discovery Science, DS 2011.
The 28 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from numerous submissions. The papers are divided into topical sections of papers on inductive inference, regression, bandit problems, online learning, kernel and margin-based methods, intelligent agents and other learning models.
Content:
Front Matter....Pages -
Editors’ Introduction....Pages 1-13
Models for Autonomously Motivated Exploration in Reinforcement Learning....Pages 14-17
On the Expressive Power of Deep Architectures....Pages 18-36
Optimal Estimation....Pages 37-37
Learning from Label Preferences....Pages 38-38
Information Distance and Its Extensions....Pages 39-39
Iterative Learning from Positive Data and Counters....Pages 40-54
Robust Learning of Automatic Classes of Languages....Pages 55-69
Learning and Classifying....Pages 70-83
Learning Relational Patterns....Pages 84-98
Adaptive and Optimal Online Linear Regression on ?1-Balls....Pages 99-113
Re-adapting the Regularization of Weights for Non-stationary Regression....Pages 114-128
Competing against the Best Nearest Neighbor Filter in Regression....Pages 129-143
Lipschitz Bandits without the Lipschitz Constant....Pages 144-158
Deviations of Stochastic Bandit Regret....Pages 159-173
On Upper-Confidence Bound Policies for Switching Bandit Problems....Pages 174-188
Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits....Pages 189-203
The Perceptron with Dynamic Margin....Pages 204-218
Combining Initial Segments of Lists....Pages 219-233
Regret Minimization Algorithms for Pricing Lookback Options....Pages 234-248
Making Online Decisions with Bounded Memory....Pages 249-261
Universal Prediction of Selected Bits....Pages 262-276
Semantic Communication for Simple Goals Is Equivalent to On-line Learning....Pages 277-291
Accelerated Training of Max-Margin Markov Networks with Kernels....Pages 292-307
Domain Adaptation in Regression....Pages 308-323
Approximate Reduction from AUC Maximization to 1-Norm Soft Margin Optimization....Pages 324-337
Axioms for Rational Reinforcement Learning....Pages 338-352
Universal Knowledge-Seeking Agents....Pages 353-367
Asymptotically Optimal Agents....Pages 368-382
Time Consistent Discounting....Pages 383-397
Distributional Learning of Simple Context-Free Tree Grammars....Pages 398-412
On Noise-Tolerant Learning of Sparse Parities and Related Problems....Pages 413-424
Supervised Learning and Co-training....Pages 425-439
Learning a Classifier when the Labeling Is Known....Pages 440-451
Erratum: Learning without Coding....Pages 452-452
Back Matter....Pages -
....