ALT10Logo The 21st International Conference
Algorithmic Learning Theory


DSLogo The 13th International Conference on Discovery Science

Canberra, Australia
October 6 - 8, 2010

ALT/ DS 2010 Schedule

Tue, 5th Oct

Wed 6th

Thu, 7th Oct

Fri, 8th Oct

Invited Talks

  1. The Blessing and the Curse of the Multiplicative Updates
    Manfred Warmuth (Wed 6th, 1330-1430)
  2. Optimal Online Prediction in Adversarial Environments
    Peter Bartlett (Thu 7th, 0900-1000)
  3. Discovery of Abstract Concepts by a Robot
    Ivan Bratko (Thu 7th, 1400-1500)
  4. Towards General Algorithms for Grammatical Inference
    Alexander Clark (Fri 8th, 0900-1000)
  5. Contrast Pattern Mining and Its Application for Building Robust Classifiers
    Kotagiri Ramamohanarao (Fri 8th, 1400-1500)

Award Talks

E.M. Gold Award

(Thu 7th, 1000-1030)

Toward a classification of finite partial-monitoring games.
Gábor Bartók, Dávid Pál and Csaba Szepesvári

Carl Smith Award

(Fri 8th, 1000-1030)

An Artificial Experimenter for Enzymatic Response Characterisation.
Chris Lovell, Gareth Jones, Steve R. Gunn, and Klaus-Peter Zauner

ALT Programme

Session 1 - Statistical Learning

(Wed 6th, 1430-1545)

  1. An algorithm for iterative selection of blocks and features.
    Pierre Alquier

  2. Bayesian active learning using arbitrary binary valued queries.
    Liu Yang, Steve Hanneke, and Jaime Carbonell

  3. Approximation stability and boosting.
    Wei Gao and Zhi-Hua Zhou

Session 2 - On-line Learning and Kernel Methods

(Wed 6th, 1610-1700)

  1. Online multiple kernel learning: algorithms and mistake bounds.
    Rong Jin, Steven Hoi, and Tianbao Yang

  2. An identity for kernel ridge regression.
    Fedor Zhdanov and Yuri Kalnishkan

Session 3 - Probably Approximately Correct Learning

(Thu 7th, 1100-1240)

  1. Distribution-dependent PAC-Bayes Priors.
    Guy Lever, François Laviolette, and John Shawe-Taylor

  2. PAC learnability of a concept class under non-atomic measures: a problem by Vidyasagar.
    Vladimir Pestov

  3. A PAC-Bayes bound for tailored density estimation.
    Matthew Higgs and John Shawe-Taylor

  4. Compressed learning with regular concept.
    Jiawei Lv, Jianwen Zhang, Fei Wang, Zheng Wang, and Changshui Zhang

Session 4 - Query Learning

(Thu 7th, 1500-1615)

  1. A lower bound for learning distributions generated by probabilistic automata.
    Borja Balle, Jorge Castro, and Ricard Gavaldà

  2. Lower bounds on learning random structures with statistical queries.
    Dana Angluin, David Eisenstat, Aryeh Kontorovich, and Lev Reyz

  3. Recursive teaching dimension, learning complexity and maximum classes.
    Thorsten Doliwa, Hans Ulrich Simon, and Sandra Zilles

Session 5 - On-line Learning

(Thu 7th, 1645-1800)

  1. Switching Investments.
    Wouter K. Koolen and Steven de Rooij

  2. Prediction under expert advice under discounted loss.
    Alexey Chernov and Fedor Zhdanov

  3. A regularization approach to metrical task systems.
    Jacob Abernethy, Peter Bartlett, Niv Buchbinder, and Isabelle Stanton

Session 6 - Inductive Inference

(Fri 8th, 1100-1240)

  1. Solutions to open questions for non-U-shaped learning with memory limitations.
    John Case and Timo Kötzing

  2. Learning without coding.
    Samuel Moelius and Sandra Zilles

  3. Learning figures with the Hausdorff metric by fractals.
    Mahito Sugiyama, Eiju Hirowatari, Hideki Tsuiki, and Akihiro Yamamoto

  4. Inductive inference of languages from samplings.
    Sanjay Jain and Efim Kimber

Session 7 - Reinforcement Learning

(Fri 8th, 1500-1615)

  1. Optimality issues of universal greedy agents with static priors.
    Laurent Orseau

  2. Consistency of feature Markov processes.
    Peter Sunehag and Marcus Hutter

  3. Algorithms for adversarial bandit problems with multiple plays.
    Taishi Uchiya, Atsuyoshi Nakamura, and Mineichi Kudo

Session 8 - Grammatical Inference and Graph Learning

(Fri 8th, 1645-1800)

  1. A spectral approach for probabilistic grammatical inference of trees.
    Raphaël Bailly, François Denis, and Amaury Habrard

  2. PageRank optimization in polynomial time by stochastic shortest path reformulation.
    Balázs Csáji, Raphaël Jungers and Vincent Blondel

  3. Inferring social networks from outbreaks.
    Dana Angluin, James Aspnes, and Lev Reyzin

DS Programme

Session 1 - Discovery

(Wed 6th, 1430-1545)

  1. Discovery of Super-Mediators of Information Diffusion in Social Networks.
    Kazumi Saito, Masahiro Kimura, Kouzou Ohara, and Hiroshi Motoda

  2. Equation Discovery for Model Identification in Respiratory Mechanics of the Mechanically Ventilated Human Lung.
    Steven Ganzert, Josef Guttmann, Daniel Steinmann, and Stefan Kramer

  3. Discovery of Conservation Laws Via Matrix Search.
    Oliver Schulte, and Mark S. Dre

Session 2 - Applications

(Wed 6th, 1610-1700)

  1. Algorithm for Detecting Significant Locations from Raw GPS Data.
    Nobuharu Kami, Nobuyuki Enomoto, Teruyuki Baba, and Takashi Yoshikawa

  2. Adapted Transfer of Distance Measures for Quantitative Structure-Activity Relationships.
    Ulrich Rückert, Tobias Girschick, Fabian Buchwald, and Stefan Kramer

Session 3 - Incremental Methods

(Thu 7th, 1100-1240)

  1. Sentiment Knowledge Discovery in Twitter Streaming Data.
    Albert Bifet, and Eibe Frank

  2. Incremental Learning of Cellular Automata for Parallel Recognition of Formal Languages.
    Katsuhiko Nakamura, and Keita Imada

  3. Efficient Visualization of Document Streams.
    Miha Grčar, Vid Podpečan, Matjaž Juršič, and Nada Lavrač

  4. Incremental Mining of Closed Frequent Subtrees.
    Viet Anh Nguyen, and Akihiro Yamamoto

Session 4 - Clustering

(Thu 7th, 1500-1615)

  1. Subgroup Discovery for Election Analysis: A Case Study in.
    Henrik Grosskreutz, Mario Boley, and Maike Krause-Traudes

  2. Gaussian Clusters and Noise: an Approach Based on the Minimum Description Length Principle.
    Panu Luosto, Jyrki Kivinen, and Heikki Mannila

  3. Integer Linear Programming Models for Constrained Clustering.
    Marianne Mueller, and Stefan Kramer

Session 5 - ML Methods I

(Thu 7th, 1645-1800)
NOTE: In Drawing Room

  1. Why Text Segment Classification Based on Part of Speech Feature Selection.
    Iulia Nagy, Katsuyuki Tanaka, and Yasuo Ariki

  2. Graph Classification Based on Optimizing Graph Spectra.
    Nguyen Duy Vinh, Akihiro Inokuchi, and Takashi Washio

  3. Concept Convergence in Empirical Domains.
    Santiago Ontañón, and Enric Plaza

Session 6 - Patterns

(Fri 8th, 1100-1240)

  1. On Enumerating Frequent Closed Patterns with Key in Multi-Relational Data.
    Hirohisa Seki, Yuya Honda, and Shinya Nagano

  2. Mining Class-Correlated Patterns for Sequence Labeling.
    Thomas Hopf, and Stefan Kramer

  3. Sparse Substring Pattern Set Discovery using Linear Programming Boosting.
    Kazuaki Kashihara, Kohei Hatano, Hideo Bannai, and Masayuki Takeda

  4. Bridging Conjunctive and Disjunctive Search Spaces for Mining a New Concise and Exact Representation of Correlated Patterns.
    Nassima Ben Younes, Tarek Hamrouni, and Sadok Ben Yahia

Session 7 - ML Methods II

(Fri 8th, 1500-1615)

  1. Topology Preserving SOM with Transductive Confidence Machine.
    Bin Tong, ZhiGuang Qin, and Einoshin Suzuki

  2. Speeding Up and Boosting Diverse Density Learning.
    James R. Foulds, and Eibe Frank

  3. Exploiting Code Redundancies in ECOC.
    Sang-Hyeun Park, Lorenz Weizsäcker, Johannes Fürnkranz

Session 8 - Problem-specific Algorithms

(Fri 8th, 1645-1800)

  1. Kaggle.
    Anthony Goldbloom

  2. A Similarity-based Adaptation of Naive Bayes for Label Ranking: Application to the Metalearning Problem of Algorithm Recommendation.
    Artur Aiguzhinov, Carlos Soares, and Ana Paula Serra

  3. ESTATE: Strategy for Exploring Labeled Spatial Datasets Using Association Analysis.
    Tomasz F. Stepinski, Josue Salazar, Wei Ding, and Denis White