研究実績

研究室学生による発表

小林真佐大,渡辺一帆,``ディリクレ過程平均法における歪み尺度の一般化,''
第39回情報理論とその応用シンポジウム, ポスターセッション,岐阜県高山市,2016年12月.

小鍋涼太,渡辺一帆,``スパースな辞書を用いたL1誤差基準のための有歪圧縮,''
第39回情報理論とその応用シンポジウム, ポスターセッション,岐阜県高山市,2016年12月.

小林真佐大,渡辺一帆,``レート歪み理論によるディリクレ過程平均法の閾値パラメータ解釈 ,''
電子情報通信学会総合大会情報・システムソサイエティ特別企画,学生ポスターセッション予稿集, p.187, 九州大学,2016年3月.

上遠野貴広, ``ディリクレ過程平均法におけるクラスタ数推定法と推定精度の解析,''
電子情報通信学会東海支部卒業研究発表会,豊橋技術科学大学,2015年3月.

河野優也, ``ε不感応損失を用いたクラスタリング法の収束性と汎化性,''
電子情報通信学会東海支部卒業研究発表会,豊橋技術科学大学,2015年3月.

学術論文

小林真佐大,渡辺一帆,``ディリクレ過程平均法のレート歪み理論による解釈,''
電子情報通信学会論文誌A,採録決定.

Kazuho Watanabe,
"Rate-distortion bounds for kernel-based distortion measures,"
Entropy, Special Issue "Information Theory in Machine Learning and Data Science", vol.19, no.7, 336, 2017.

Kazuho Watanabe,
"Projection to mixture families and rate-distortion bounds with power distortion measures,"
Entropy, Special Issue "Information Geometry II", vol.19, no.6, 262, 2017.

Kazuho Watanabe and Shiro Ikeda,
"Rate-distortion functions for gamma-type sources under absolute-log distortion measure,"
IEEE Transactions on Information Theory, vol.62, no.10, pp.5496-5502, 2016.

Makoto Uemura, Ryosuke Itoh, Longyin Xu, Masanori Nakayama, Hsiang-Yun Wu, Kazuho Watanabe, Shigeo Takahashi, Issei Fujishiro,
"TimeTubes: Visualization of polarization variations in blazars,"
Galaxies, vol. 4, no. 3, article-id:23, 2016.

藤代一成,高橋成雄,渡辺一帆,Hsiang-Yun Wu,
"スパースモデリングと情報可視化,"
電子情報通信学会誌,vol.99, No.5, pp.466-470, 2016.

Kazuho Watanabe, Hsiang-Yun Wu, Shigeo Takahashi, and Issei Fujishiro,
"Asymmetric biclustering with constrained von Mises-Fisher models,"
Journal of Physics: Conference Series, vol.699, 012018, 2016.

Makoto Uemura, Koji S. Kawabata, Shiro Ikeda, Keiichi Maeda, Hsiang-Yun Wu, Kazuho Watanabe, Shigeo Takahashi, Issei Fujishiro,
"Data-driven approach to Type Ia supernovae: variable selection on the peak luminosity and clustering in visual analytics,"
Journal of Physics: Conference Series, vol.699, 012009, 2016.

Kazuho Watanabe,
"Rate-distortion bounds for epsilon-insensitive distortion measures,"
IEICE Transactions on Fundamentals, Vol.E99-A, No.1, pp.370-377, Jan. 2016.

Kazuho Watanabe and Teemu Roos,
"Achievability of asymptotic minimax regret by horizon-dependent and horizon-independent strategies,"
Journal of Machine Learning Research, Vol.16, pp.2357-2375, 2015.

Kazuho Watanabe,
"Vector quantization based on epsilon-insensitive mixture models,"
Neurocomputing, vol.165, pp.32-37, 2015.

Takuya Konishi, Takatomi Kubo, Kazuho Watanabe, and Kazushi Ikeda,
"Variational Bayesian inference algorithms for infinite relational model of network data,"
IEEE Transactions on Neural Networks and Learning Systems, Vol.26, No.9, pp.2176-2181, 2015.

能野琴,Hsiang-Yun WU,渡辺一帆,高橋成雄,藤代一成,
"グラフスペクトル解析を用いた平行座標系の軸縮約,"
画像電子学会誌, Vol.44,No.3,pp.447-456,2015年8月.

Atsushi Miyamoto, Kazuho Watanabe, Kazushi Ikeda, and Masa-aki Sato,
"Variational inference with ARD prior for NIRS diffuse optical tomography,"
IEEE Transactions on Neural Networks and Learning Systems, Vol.26, No.5, pp.1109-1114, 2015.

Kazuho Watanabe and Shiro Ikeda,
"Entropic risk minimization for nonparametric estimation of mixing distributions,"
Machine Learning, Vol.99, No.1, pp.119-136, 2015.

国際会議録

Kazuho Watanabe,
"Rate-distortion tradeoffs under kernel-based distortion measures,"
Proc. of the 2017 IEEE International Symposium on Information Theory (ISIT2017), pp.1928-1932, Aachen, Germany, 2017.

Hsiang-Yun Wu, Yusuke Niibe, Kazuho Watanabe, Shigeo Takahashi, Makoto Uemura, and Issei Fujishiro,
"Making many-to-many parallel coordinate plots scalable by asymmetric biclustering,"
Proceedings of the 10th IEEE Pacific Visualization Symposium (PacificVis 2017), pp.305-309, Seoul, Korea, 2017.

Kazuho Watanabe,
"Constant-width rate-distortion bounds for power distortion measures,"
Proceedings of the IEEE Information Theory Workshop (ITW2016), pp.106-110, Cambridge, U.K., 2016.

Yusuke Niibe, Hsiang-Yun Wu, Kazuho Watanabe, Shigeo Takahashi, Issei Fujishiro,
"Making many-to-many parallel coordinate plots scalable by asymmetric biclustering"
International Meeting on High-Dimensional Data-Driven Science (HD3-2015), Kyoto, Japan, 2015 (poster).

Kazuho Watanabe, Hsiang-Yun Wu, Yusuke Niibe, Shigeo Takahashi, and Issei Fujishiro,
"Biclustering Multivariate Data for Correlated Subspace Mining,"
Proceedings of the 8th IEEE Pacific Visualization Symposium (PacificVis 2015), pp.287-294, April 14-17, Hangzhou, China, 2015.

Shinichi Nakajima, Issei Sato, Masashi Sugiyama, Kazuho Watanabe, and Hiroko Kobayashi,
"Analysis of variational Bayesian latent Dirichlet allocation: weaker sparsity than MAP,"
Advances in Neural Information Processing Systems (NIPS2014), pp.1224-1232, December 8-13, Montreal, Canada, 2014.

Koto Nohno, Hsiang-Yun Wu, Kazuho Watanabe, Shigeo Takahashi, and Issei Fujishiro,
"Spectral-based contractible parallel coordinates,"
Proceedings of the 18th International Conference on Information Visualisation (iV2014), pp.7-12, Paris, France, July 15-18, 2014.

Andrew Barron, Teemu Roos, and Kazuho Watanabe,
"Bayesian Properties of Normalized Maximum Likelihood and its Fast Computation,"
Proceedings of the IEEE International Symposium on Information Theory (ISIT), pp.1667-1671, Honolulu, Hawaii, USA, June 29-July 7, 2014.

招待講演、チュートリアル講演等

Kazuho Watanabe, "Rate-distortion theoretic views of learning problems,"
Proc. of 2016 Workshop on Information Theoretic Methods in Science and Engineering, pp.41-44, Helsinki, Finland, 2016.

渡辺一帆,"MDLの効率的計算のための事前分布設定"
電子情報通信学会総合大会,企画セッション「記述長最小原理の新展開」,基礎・境界講演論文集,pp.SS5-SS7, 九州大学,2016年3月.

Kazuho Watanabe,
"Rate-Distortion Analysis for Kernel-Based Distortion Measures,"
Proceedings of 2015 Workshop on Information Theoretic Methods in Science and Engineering, pp.46-49, Copenhagen, Denmark, 2015.

Kazuho Watanabe,
"Rate-Distortion Analysis for an Epsilon-Insensitive Loss Function,"
Proceedings of 2014 Workshop on Information Theoretic Methods in Science and Engineering, pp.23-26, Honolulu, Hawaii, USA, 2014.

国内会議発表

吉田智晴, 渡辺一帆, 梅村恭司, ``角転送行列を用いた格子状マルコフ確率場の厳密計算,''(英題:``Exact calculation of grid-structured Markov random field model by corner transfer matrix method,'')
電子情報通信学会情報論的学習理論と機械学習研究会, 東京工業大学, 2017年3月6日, 信学技法,IBISML2016-101, pp.9-16, 2017.

渡辺一帆,``レート歪み理論と一般化事後分布,''
科研費シンポジウム:統計的モデリングと計算アルゴリズムの数理と展開,名古屋大学,2017年2月19日.

吉田智晴, 渡辺一帆, 梅村恭司, ``角転送行列繰り込み群法の格子状マルコフ確率場への適用,''
情報論的学習理論ワークショップ,ディスカッショントラック,京都大学,2016年11月.

梶大介,渡辺一帆,``変分ベイズ法を用いたクラスタ構造変化の抽出,''(英題:``Extraction of Cluster Structural Changes using Variational Bayes,'')
情報論的学習理論ワークショップ, 京都大学, 2016年11月17日, 信学技法,IBISML2016-78, pp.229-233, 2016.

渡辺一帆,``Rate-Distortion Bounds for Distortion Measures with Kernel Feature Mapping,''
第38回情報理論とその応用シンポジウム, pp.73-77,2015年11月.

植村誠, 前田啓一, Hsiang-Yun Wu, 渡辺一帆, 高橋成雄, 藤代一成,
``バイクラスタリングの対話型可視化ツールを用いたIa 型超新星の分類''
日本天文学会2015年秋季年会, 甲南大学, 2015年9月.

中島伸一,佐藤一誠,杉山将,渡辺一帆,小林寛子,
``変分ベイズLDAの漸近解析,''(英題:``Asymptotic Analysis of Variational Bayesian Latent Dirichlet Allocation,'')
電子情報通信学会情報論的学習理論と機械学習研究会, 名古屋大学
信学技法,IBISML2014-64, pp.219-226, 2014.

▲ページトップに戻る