Committee 
Date Time 
Place 
Paper Title / Authors 
Abstract 
Paper # 
NC, IBISML, IPSJMPS, IPSJBIO [detail] 
20190617 17:00 
Okinawa 
Okinawa Institute of Science and Technology 
Adaptive Discretization based Predictive Sequence Mining for Continuous Time Series Yoshikazu Shibahara, Takuto Sakuma (NIT), Ichiro Takeuchi (NIT/RIKEN/NIMS), Masayuki Karasuyama (NIT/NIMS) 
In recent years, improvement of sensor performance and spread of portable devices such as smartphones enable us to easil... [more] 
IBISML20199 pp.5764 
IBISML 
20181105 15:10 
Hokkaido 
Hokkaido Citizens Activites Center (Kaderu 2.7) 
[Poster Presentation]
Distance Metric Learning Between Graphs Based on Subgraph Tomoki Yoshida (NITech), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST) 
A standard approach to evaluating distance between two graphs is to use common subgraphs contained in the two graphs. Fo... [more] 
IBISML201864 pp.151158 
NC, IBISML, IPSJBIO, IPSJMPS [detail] 
20180613 10:00 
Okinawa 
Okinawa Institute of Science and Technology 
Active Level Set Estimation with Multifidelity Evaluations Shion Takeno (Nitech), Hitoshi Fukuoka (Nagoya Univ.), Yuhki Tsukada (Nagoya Univ./JST), Toshiyuki Koyama (Nagoya Univ.), Motoki Shiga (Gifu Univ./JST/RIKEN), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST) 
Level set estimation is a problem to identify a level set of an unknown function, which is defined by whether the functi... [more] 
IBISML20181 pp.18 
IBISML 
20180306 11:15 
Fukuoka 
Nishijin Plaza, Kyushu University 
Selecting discriminative and representative patterns from sequence data: an approach based on classification model and morse complex Masayuki Karasuyama (Nagoya Inst. of Tech./NIMS/JST), Ichiro Takeuchi (Nagoya Inst. of Tech./NIMS/RIKEN) 
We study classification problem on the sequences of continuous observations. In particular, we are interested in identif... [more] 
IBISML2017101 pp.7784 
IBISML 
20171110 13:00 
Tokyo 
Univ. of Tokyo 
Safe Screening for Large Margin Metric Learning Tomoki Yoshida (NITech), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST) 
Large margin metric learning learns the optimal Mahalanobis distance for classification problem based on the margin maxi... [more] 
IBISML201764 pp.219226 
NC, IPSJBIO, IBISML, IPSJMPS [detail] 
20170625 11:25 
Okinawa 
Okinawa Institute of Science and Technology 
Costsensitive Bayesian optimization for multiple objectives and its application to material science Tomohiro Yonezu (NITech), Tomoyuki Tamura, Ryo Kobayashi (NITech/NIMS), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST) 
We consider solving a set of blackbox optimization problems in which each problem has a similar objective function each... [more] 
IBISML201710 pp.207213 
IBISML 
20170307 10:00 
Tokyo 
Tokyo Institute of Technology 
Safe Pruning Rule for Predictive Sequential Pattern Mining and Its Application to Biologging Data Analysis Kaoru Kishimoto (NITech), Masayuki Karasuyama (NIT), Kazuya Nakagawa (NITech), Kotaro Kimura (Osaka Univ.), Ken Yoda (Nagoya Univ.), Yuta Umezu, Shinsuke Kajioka (NITech), Koji Tsuda (UTokyo), Ichiro Takeuchi (NITech) 
Recently, the analysis for timeseries logging data of animal behaviors, called biologging data, has attracted a wide a... [more] 
IBISML2016105 pp.4148 
IBISML 
20170307 11:00 
Tokyo 
Tokyo Institute of Technology 
A study on minimizing size of sparse model optimization problem: exploiting safe rules for keeping and removing variables Masayuki Karasuyama (NIT/NIMS/JST), Atsushi Shibagaki (NIT), Ichiro Takeuchi (NIT/NIMS/RIKEN/NIMS) 
[more] 
IBISML2016107 pp.5762 
IBISML 
20161116 15:00 
Kyoto 
Kyoto Univ. 
Exploring GB Energies using Gaussian Process Masayuki Karasuyama (NIT/NIMS/JST Sakigake), Tomoyuki Tamura, Ryo Kobayashi, Ichiro Takeuchi, Masanobu Nakayama (NIT/NIMS) 
[more] 
IBISML201667 pp.151154 
IBISML 
20161117 14:00 
Kyoto 
Kyoto Univ. 
[Poster Presentation]
Estimating Proton Conductivity in Crystals by using Guassian Process and Dynamic Programming Kenta Kanamori (NITech), Kazuaki Toyoura (Kyoto Univ.), Shinichi Nakajima (TU Berlin), Atsuto Seko (Kyoto Univ.), Masayuki Karasuyama (NITech), Akihide Kuwabara (JFCC), Junya Honda (Tokyo Univ.), Kazuki Shitara (JFCC), Motoki Shiga (Gifu Univ.), Ichiro Takeuchi (NITech) 
In material science, $proton conductivity$ is very important property for designing new battery and it is defined as max... [more] 
IBISML201673 pp.191198 
PRMU, IPSJCVIM, IBISML [detail] 
20160905 15:45 
Toyama 

Sparse learning for pattern mining problem by using Safe Pattern Pruning method Kazuya Nakagawa, Shinya Suzumura, Masayuki Karasuyama (NIT), Koji Tsuda (Univ. of Tokyo), Ichiro Takeuchi (NIT) 
In this paper we study predictive pattern mining problems where the goal is to construct a predictive model based on a s... [more] 
PRMU201670 IBISML201625 pp.127134 
NC, IPSJBIO, IBISML, IPSJMPS [detail] 
20160706 10:50 
Okinawa 
Okinawa Institute of Science and Technology 
Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling Atsushi Shibagaki, Masayuki Karasuyama (NIT), Kohei Hatano (Kyushu Univ.), Ichiro Takeuchi (NIT) 
[more] 
IBISML20164 pp.201208 
IBISML 
20151126 15:00 
Ibaraki 
Epochal Tsukuba 
[Poster Presentation]
Selective sampling by using Gaussian Process and its application to material science Daisuke Hirano (NIT), Kazuaki Toyoura (Nagoya Univ.), Atsuto Seko (Kyoto Univ.), Motoki Shiga (Gifu Univ.), Akihide Kuwabara (JFCC), Masayuki Karasuyama (NIT), Kazuki Shitara (Kyoto Univ.), Ichiro Takeuchi (NIT) 
Various physical phenomena and properties of an unknown material are often revealed by exhaustively evaluating the entir... [more] 
IBISML201566 pp.99106 
IBISML 
20151127 14:00 
Ibaraki 
Epochal Tsukuba 
[Poster Presentation]
Clustering Features based on Simultaneous Manifold Learning Masayuki Karasuyama (NIT), Hiroshi Mamitsuka (Kyoto Univ.) 
[more] 
IBISML201579 pp.195201 
NC, IPSJBIO, IBISML, IPSJMPS (Joint) [detail] 
20150623 14:15 
Okinawa 
Okinawa Institute of Science and Technology 
Efficient sparse learning for combinatorial model by using safe screening approach Kazuya Nakagawa, Shinya Suzumura, Masayuki Karasuyama, Ichiro Takeuchi (NIT) 
In a variety of machine learning tasks, it has been desired to incorporate highorder interaction effects of multiple co... [more] 
IBISML201510 pp.6368 
IBISML 
20130305 16:30 
Aichi 
Nagoya Institute of Technology 
Similarity adaptation for label propagation based on local linear reconstruction Masayuki Karasuyama, Hiroshi Mamitsuka (Kyoto Univ.) 
Label propagation is one of the stateoftheart methods for semisupervised
learning,
which estimates labels by pro... [more] 
IBISML2012109 pp.115121 
IBISML 
20121107 15:30 
Tokyo 
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. 
Propagating Labels via Sparse Combination of Multiple Graphs Masayuki Karasuyama, Hiroshi Mamitsuka (Kyoto Univ.) 
Label propagation is a widely accepted approach in graphbased
semisupervised learning that predicts labels of nodes ... [more] 
IBISML201258 pp.171178 
PRMU, IBISML, IPSJCVIM [detail] 
20110906 15:50 
Hokkaido 

Canonical Dependency Analysis based on Squaredloss Mutual Information Masayuki Karasuyama, Masashi Sugiyama (Tokyo Inst. of Tech.) 
Canonical correlation analysis (CCA) is a classical technique to iteratively find projection directions for two sets of ... [more] 
PRMU201179 IBISML201138 pp.173180 
IBISML 
20110328 15:00 
Osaka 
Nakanoshima Center, Osaka Univ. 
A Study on Positionbased Adaptive Weighting for Ranking SVM Masayuki Karasuyama, Takuya Hasegawa, Tsukasa Matsuno, Ichiro Takeuchi (Nagoya Inst. of Tech.) 
This paper presents a novel training algorithm for ranking support vector machine (ranking SVM). The focus is on how to ... [more] 
IBISML2010115 pp.7783 
IBISML 
20101104 15:00 
Tokyo 
IIS, Univ. of Tokyo 
[Poster Presentation]
A Study on Simultaneous Feature Selection for CostSensitive Classifiers Using MixedNorm Regularization Toru Sugiura, Kazuaki Koide, Tatsuya Hongo, Masayuki Karasuyama, Ichiro Takeuchi (NIT) 
Costsensitive learning is useful for binary classification when the
costs of missclassifications are not symmetric. I... [more] 
IBISML201070 pp.8390 