Algorithmic Learning Theory

Yoav Freund is Professor of Computer Science at the University of California, San Diego.

Invited Papers.- On Iterative Algorithms with an Information Geometry Background.- Visual Analytics: Combining Automated Discovery with Interactive Visualizations.- Some Mathematics behind Graph Property Testing.- Finding Total and Partial Orders from Data for Seriation.- Computational Models of Neural Representations in the Human Brain.- Regular Contributions.- Generalization Bounds for Some Ordinal Regression Algorithms.- Approximation of the Optimal ROC Curve and a Tree-Based Ranking Algorithm.- Sample Selection Bias Correction Theory.- Exploiting Cluster-Structure to Predict the Labeling of a Graph.- A Uniform Lower Error Bound for Half-Space Learning.- Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces.- Learning and Generalization with the Information Bottleneck.- Growth Optimal Investment with Transaction Costs.- Online Regret Bounds for Markov Decision Processes with Deterministic Transitions.- On-Line Probability, Complexity and Randomness.- Prequential Randomness.- Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor.- Nonparametric Independence Tests: Space Partitioning and Kernel Approaches.- Supermartingales in Prediction with Expert Advice.- Aggregating Algorithm for a Space of Analytic Functions.- Smooth Boosting for Margin-Based Ranking.- Learning with Continuous Experts Using Drifting Games.- Entropy Regularized LPBoost.- Optimally Learning Social Networks with Activations and Suppressions.- Active Learning in Multi-armed Bandits.- Query Learning and Certificates in Lattices.- Clustering with Interactive Feedback.- Active Learning of Group-Structured Environments.- Finding the Rare Cube.- Iterative Learning of Simple External Contextual Languages.- Topological Properties of Concept Spaces.- Dynamically Delayed Postdictive Completeness and Consistency in Learning.- Dynamic Modeling in Inductive Inference.- Optimal Language Learning.- Numberings Optimal for Learning.- Learning with Temporary Memory.- Erratum: Constructing Multiclass Learners from Binary Learners: A Simple Black-Box Analysis of the Generalization Errors.