DMSS2009 Program

Time for presentation

1hour
Invited talks
30min
regular presentation

July 7

13:20-13:30
Opening Remark
13:30-15:00
Session 1
Efficient Exploration through Active Learning for Value Function Approximation in Reinforcement Learning
Takayuki Akiyama, Hirotaka Hachiya, and Masashi Sugiyama (Tokyo Institute of Technology)
Visual Inspection of Precision Instruments by Least-Squares Outlier Detection
Masafumi Takimoto, Masakazu Matsugu (Canon), and Masashi Sugiyama (Tokyo Institute of Technology)
Extracting Phases of Financial Markets
Teruko Takada (Osaka City University)
15:00-15:15
Break
15:15-16:15
Session 2
Recent Topics on BDDs/ZDDs for Data Mining and Knowledge Discovery (Invited Talk)
Shin-ichi Minato (Hokkaido University)
16:15-16:30
Break
16:30-17:30
Session 3
Dimensionality Reduction for Density Ratio Estimation in High-dimensional Spaces
Masashi Sugiyama (Tokyo Institute of Technology), Motoaki Kawanabe (Fraunhofer Institute FIRST), and Pui Ling Chui (Tokyo Institute of Technology)
Sufficient Dimension Reduction via Squared-loss Mutual Information Estimation
Taiji Suzuki (University of Tokyo) and Masashi Sugiyama (Tokyo Institute of Technology)

July 8

10:00-11:30
Session 4
Identification of an Exogenous Variable in a Linear non-Gaussian Structural Equation Model
Shohei Shimizu (Osaka University), Aapo Hyvarinen (University of Helsinki), Yoshinobu Kawahara (Tokyo Institute of Technology), and Takashi Washio (Osaka University)
Maximum Likelihood Estimation for Failed-Link Detection in Communication Networks
Shohei Hido (Kyoto University, IBM Research) and Yutaka Takahashi (Kyoto University)
Gaussian Mixture Models and VC Dimensions
Yohji Akama (Tohoku University)
11:30-13:30
Lunch
13:30-14:30
Session 5
Invited Talk
Katsutoshi Yada (Kansai University)
14:30-14:45
Break
14:45-16:15
Session 6
Monolithic and Partial Compilation Methods for Probabilistic Inference of Bayesian Networks using ZBDDs
Daisuke Tokoro, Kiyoharu Hamaguchi, Toshinobu Kashiwabara (Osaka University), and Shin-ichi Minato (Hokkaido University)
Pattern Discovery from a Single Graph with Quantitative Itemsets
Yuuki Miyoshi, Tomonobu Ozaki, and Takenao Ohkawa (Kobe University)
Mining Frequent Patterns from Linear Graphs
Yasuo Tabei, Daisuke Okanohara (University of Tokyo), and Koji Tsuda (National Institute of Advanced Industrial Science and Technology)
16:15-16:20
Closing Remark