Publication List

Articles

M. Kobayashi, K. Watanabe
"Generalized Dirichlet-process-means for f-separable distortion measures,"
Neurocomputing, vol.458, pp.667-689, 2021. <pdf, arXiv>

M. Kikuchi, K. Kawakami, K. Watanabe, M. Yoshida, K. Umemura
"Unified likelihood ratio estimation for high- to zero-frequency N-grams,"
IEICE Transactions on Fundamentals, vol.E104-A, no.08, pp.1059-1074, 2021. <link, TUT Repository>

T. Yoshida, K. Watanabe,
"Empirical Bayes Estimation for L_1 Regularization: A Detailed Analysis in the One-Parameter Lasso Model,"
IEICE Transactions on Fundamentals, Special Section on Information Theory and Its Applications, Vol.E101-A, No.12, pp.2184-2191, Dec. 2018. <link, TUT Repository>

I. Fujishiro, N. Sawada, M. Nakayama, H-Y. Wu, K. Watanabe, S. Takahashi, M. Uemura,
"TimeTubes: Visual Exploration of Observed Blazar Datasets,"
Journal of Physics: Conference Series, vol.1036, 012011, 2018.<pdf>

M. Kobayashi, K. Watanabe, "A rate-distortion theoretic view of Dirichlet process means clustering,"
IEICE Transactions on Fundamentals, vol. J100-A, no.12 , pp.475-486, 2017 (in Japanese). <link, TUT Repository>

K. 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.<link>

K. 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.<link>

K. Watanabe, S. 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.<link>

I. Fujishiro, S. Takahashi, K. Watanabe, H-Y. Wu, "Sparse Modeling and Information Visualization,"
Journal of IEICE, vol.99, No.5, pp.466-470, 2016.<link>

K. Watanabe, H-Y. Wu, S. Takahashi, I. Fujishiro,
"Asymmetric biclustering with constrained von Mises-Fisher models,"
Journal of Physics: Conference Series, vol.699, 012018, 2016.<pdf>

M. Uemura, K. S. Kawabata, S. Ikeda, K. Maeda, H-Y. Wu, K. Watanabe, S. Takahashi, I. 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.<pdf>

K. Watanabe, "Rate-Distortion Bounds for Epsilon-Insensitive Distortion Measures,"
IEICE Transactions on Fundamentals, Vol.E99-A, No.1, pp.370-377, Jan. 2016.<link>

K. Watanabe, T. Roos, "Achievability of Asymptotic Minimax Regret by Horizon-Dependent and Horizon-Independent Strategies,"
Journal of Machine Learning Research, Vol.16, pp.2357-2375, 2015.<pdf>

K. Watanabe, "Vector Quantization Based on Epsilon-Insensitive Mixture Models,"
Neurocomputing, Vol.165, pp.32-37, 2015.<pdf>

T. Konishi, T. Kubo, K. Watanabe, K. 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. <link>

K. Nohno, H-Y. Wu, K. Watanabe, S. Takahashi, I. Fujishiro, "Axis Contraction of Parallel Coordinates Using Spectral Graph Analysis,"
The Journal of the Institute of Image Electronics Engineers of Japan, Vol.44, No.3, pp.447-456, Aug. 2015 (in Japanese).<link>

A. Miyamoto, K. Watanabe, K. Ikeda, M. 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. <link>

K. Watanabe, S. Ikeda, "Entropic risk minimization for nonparametric estimation of mixing distributions,"
Machine Learning, Vol. 99, No. 1, pp. 119-136, 2015. <pdf>

K. Watanabe, "An alternative view of variational Bayes and asymptotic approximations of free energy,"
Machine Learning, Vol. 86, No. 2, pp. 273-293, 2012. <doi>

K. Watanabe, M. Okada, "Approximate Bayesian estimation of varying binomial process,"
IEICE Transactions on Fundamentals, Vol. E94-A, No. 12, pp. 2879-2885, Dec. 2011. <doi, link>

K. Watanabe, M. Okada, K. Ikeda, "Divergence measures and a general framework for local variational approximation,"
Neural Networks, Vol. 24, No. 10, pp. 1102-1109, 2011.<doi>

D. Kaji, K. Watanabe, S. Watanabe, "Phase transition of variational Bayes learning in Bernoulli mixture,"
Australian Journal of Intelligent Information Processing Systems, vol. 11, no. 4, pp. 35-40, 2010. <pdf>

S. Akaho, K. Watanabe, M. Okada, "Data analysis method on space of exponential family distributions,"
Proceedings of the Institute of Statistical Mathematics, vol. 58, no. 2, pp. 167-183, 2010 (in Japanese). <pdf>

K. Watanabe, T. Kubo, M. Okada, "MAP estimation method for binary varying source using smoothing prior,"
IEICE Transactions on Fundamentals, vol. J93-A, no. 4, pp. 326-330, 2010 (letter, in Japanese). <link>

K. Watanabe, S. Akaho, S. Omachi, M. Okada, "Variational Bayesian mixture model on a subspace of exponential family distributions,"
IEEE Transactions on Neural Networks, vol. 20, no. 11, pp. 1783-1796, 2009. <doi>

K. Watanabe, H. Tanaka, K. Miura, M. Okada, "Transfer matrix method for instantaneous spike rate estimation,"
IEICE Transactions on Information and Systems, vol. E92-D, no. 7, pp. 1362-1368, Jul. 2009. <doi>

K. Watanabe, M. Shiga, S. Watanabe, "Upper bound for variational free energy of Bayesian networks,"
Machine Learning, vol. 75, no. 2, pp. 199-215, 2009.<doi>

K. Katahira, K. Watanabe, M. Okada, "Deterministic annealing variant of variational Bayes method,"
Journal of Physics: Conference Series, 95, 012015, 2008. <pdf>

K. Watanabe, S. Watanabe, "Stochastic complexity for mixture of exponential families in generalized variational Bayes,"
Theoretical Computer Science, Vol. 387, pp. 4-17, 2007.<doi>
[Invited paper for the special issue on ALT2005]

K. Watanabe, S. Watanabe, "Estimating the data region using minimum and maximum values,"
Interdisciplinary Information Sciences, Vol. 13, No. 2, pp. 151-161, 2007.<pdf>

K. Watanabe, S. Watanabe, "Stochastic complexities of general mixture models in variational Bayesian learning,"
Neural Networks, Vol. 20, No. 2, pp. 210-219, 2007. <doi>
[Best Paper Award from Japanese Neural Network Society (2008)]

T. Hosino, K. Watanabe, S. Watanabe, "Stochastic complexity of hidden Markov models on the variational Bayesian learning,"
IEICE Transactions on Information and Systems,Vol. J89-D, No. 6, pp. 1279-1287, 2006 (in Japanese).<link>

K. Watanabe, S. Watanabe, "Stochastic complexities of Gaussian mixtures in variational Bayesian approximation,"
Journal of Machine Learning Research, Vol. 7(Apr), pp. 625--644, 2006. <pdf>

K. Watanabe, S. Watanabe, "Upper bounds of Bayesian generalization errors in reduced rank regression,"
IEICE Transactions on Fundamentals, Vol. J86-A, No. 3, pp. 278-287, 2003 (in Japanese). <link>

International Conference Proceedings

Kazuho Watanabe, " Statistical Learning of the Insensitive Parameter in Support Vector Models,"
Proc. of the 2021 IEEE International Symposium on Information Theory (ISIT2021), pp.2501-2506, Virtual conf. (Melbourne, Victoria, Australia), Jul. 12-20, 2021.

Masahiro Kobayashi, Kazuho Watanabe,
"Unbiased Estimation Equation under f-Separable Bregman Distortion Measures,"
Proc. of the IEEE Information Theory Workshop (ITW2020), pp.311-315, Virtual conf. (Riva del Garda, Italy), Apr. 11-15, 2021.

Shigeo Takahashi, Akane Uchita, Kazuho Watanabe, Masatoshi Arikawa,
"Context-Aware Placement of Items with Gaze-Based Interaction,"
Proc. of the 13th International Symposium on Visual Information Communication and Interaction (VINCI'20), Article no.12, Virtual conf. (Eindhoven, Netherlands), Dec. 8-10, 2020.

Daisuke Kaji, Kazuho Watanabe, Masahiro Kobayashi,
"Multi-Decoder RNN Autoencoder Based on Variational Bayes Method,"
Proc. of 2020 IEEE International Joint Conference on Neural Networks, Virtual conf. (Glasgow, UK), Jul. 19-24, 2020.

K. Watanabe, "Discrete Optimal Reconstruction Distributions for Itakura-Saito Distortion Measure,''
Proc. of the 2020 IEEE International Symposium on Information Theory (ISIT2020), pp.2399-2404, Los Angeles, California, USA, Jun. 21-26, 2020.

K. Konagayoshi, K. Watanabe,
"Minimax Online Prediction of Varying Bernoulli Process under Variational Approximation,"
Proc. of The Eleventh Asian Conference on Machine Learning (ACML2019), PMLR 101, pp.141-156, Nagoya, Japan, Nov. 17-19, 2019.

M. Kobayashi, K. Watanabe,
"Generalized Dirichlet-Process-Means for Robust and Maximum Distortion Criteria"
Proc. of the International Symposium on Information Theory and Its Applications (ISITA2018), pp.45-49, Singapore, 2018.

T. Yoshida, T. Moriya, K. Watanabe, Y. Shinohara, Y. Yamaguchi, Y. Aono,
"Automatic DNN Node Pruning Using Mixture Distribution-based Group Regularization"
Proc. of Interspeech, pp.1269-1273, Hyderabad, India, 2018.

R. Konabe, K. Watanabe,
"Sparse regression code with sparse dictionary for absolute error criterion,"
Proc. of the 2018 IEEE International Symposium on Information Theory (ISIT2018), pp.1515-1519, Vail, Colorado, USA, 2018.

K. 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.

H-Y. Wu, Y. Niibe, K. Watanabe, S. Takahashi, M. Uemura, and I. 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.

K. Watanabe, "Rate-distortion theoretic views of learning problems,"
Proc. of 2016 Workshop on Information Theoretic Methods in Science and Engineering, pp.41-44, 2016.
[Invited]

K. 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.

L. Xu, M. Nakayama, H-Y. Wu, K. Watanabe, S. Takahashi, M. Uemura, I. Fujishiro,
"TimeTubes: Design of a visualization tool for time-dependent, multivariate blazar datasets,"
Proc. of NICOGRAPH International 2016, 2016.

K.Watanabe, "Rate-Distortion Analysis for Kernel-Based Distortion Measures,"
Proceedings of 2015 Workshop on Information Theoretic Methods in Science and Engineering, pp.46-49, 2015.
[Invited]

K. Watanabe, H-Y. Wu, Y. Niibe, S. Takahashi, I. Fujishiro, "Biclustering Multivariate Data for Correlated Subspace Mining,"
Proceedings of the 8th IEEE Pacific Visualization Symposium (PacificVis 2015), pp.287-294, 2015.

S. Nakajima, I. Sato, M. Sugiyama, K. Watanabe, H. 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.

K. Nohno, H-Y. Wu, K. Watanabe, S. Takahashi, I. Fujishiro, "Spectral-based contractible parallel coordinates,"
Proceedings of the 18th International Conference on Information Visualisation (iV2014), pp.7-12, July 15-18, Paris, France, 2014.

K. 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, 2014.
[Invited]

A. R. Barron, T. Roos, K. Watanabe, "Bayesian Properties of Normalized Maximum Likelihood and its Fast Computation,"
Proceedings of the IEEE International Symposium on Information Theory (ISIT), Honolulu, Hawaii, USA, pp.1667-1671, 2014.

K. Watanabe, T. Roos, P. Myllymäki, "Achievability of Asymptotic Minimax Regret in Online and Batch Prediction,"
Proceedings of the 5th Asian Conference on Machine Learning (ACML2013), pp. 181-196, Canberra, Australia, 2013.

K. Watanabe, "Vector Quantization Using Mixture of Epsilon-Insensitive Components,"
Proceedings of International Conference on Neural Information Processing (ICONIP2013), Part III, LNCS 8228, pp. 85-92, Daegu, Korea, 2013.

K. Watanabe, "Rate-Distortion Bounds for an Epsilon-Insensitive Distortion Measure,"
Proceedings of the IEEE Information Theory Workshop (ITW), pp. 679-683, Sevilla, Spain, 2013.

K. Watanabe, T. Roos, P. Myllymäki, "Achievability of Asymptotic Minimax Optimality in Online and Batch Coding,"
Proceedings of 2013 Workshop on Information Theoretic Methods in Science and Engineering (WITMSE13), pp. 63-67, 2013.
[Invited]

K. Watanabe, S. Ikeda, "Rate-Distortion Function for Gamma Sources under Absolute-Log Distortion Measure,"
Proceedings of the 2013 IEEE International Symposium on Information Theory, Istanbul, Turkey, pp. 2557-2561, 2013.

A. Miyamoto, K. Watanabe, K. Ikeda, "Packet Loss Rate Estimation with Active and Passive Measurements,"
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC), Hollywood, California, USA, 2012.

K. Watanabe, S. Ikeda, "Convex formulation for nonparametric estimation of mixing distribution,"
Proceedings of 2012 Workshop on Information Theoretic Methods in Science and Engineering (WITMSE12), pp. 36-39, 2012.
[Invited]

K. Watanabe, "Minimum variational stochastic complexity and average generalization error in latent variable models,"
Proceedings of 2011 Workshop on Information Theoretic Methods in Science and Engineering (WITMSE11), pp. 75-78, 2011.
[invited]

A. Miyamoto, K. Watanabe, K. Ikeda, M. Sato, "Phase diagrams of a variational Bayesian approach with ARD prior in NIRS-DOT,"
International Joint Conference on Neural Networks, San Jose, California, USA, pp. 1230-1236, 2011.
[selected for oral presentation]

K. Watanabe, "An alternative view of variational Bayes and minimum variational stochastic complexity,"
Proceedings of 2010 Workshop on Information Theoretic Methods in Science and Engineering (WITMSE10), 2010.
[invited]

K. Watanabe, S. Akaho, S. Omachi, M. Okada, "Simultaneous Clustering and Dimensionality Reduction Using Variational Bayesian Mixture Model,"
Proc. of International Federation of Classification Societies 2009 Conference.
Classification as a Tool for Research, Studies in Classification, Data Analysis, and Knowledge Organization, Part 2, 81-89, 2010.
[Best Paper Method Award from The German Classification Society (2010)]

K. Watanabe, M. Okada, ``Firing Rate Estimation Using an Approximate Bayesian Method,''
Proc. of ICONIP 2008, Part I, LNCS 5506, pp. 655-662, 2009.

K. Watanabe, S. Akaho, M. Okada, "Clustering on a subspace of exponential family using variational Bayes method,"
Proceedings of International Conference on Information Theory and Statistical Learning(ITSL2008),pp. 10-16, 2008.

K. Katahira, K. Watanabe, M. Okada, "Deterministic Annealing Variant of Variational Bayes Method,"
Proceedings of International Workshop on Statistical-Mechanical Informatics (IW-SMI2007), Kyoto, Japan, pp. 65-73, 2007.

T. Hosino, K. Watanabe, S. Watanabe "Free energy of stochastic context free grammar on variational Bayes,"
Proceedings of International Conference on Neural Information Processing (ICONIP2006), Hong Kong, China, pp. 407-416, 2006.

K. Watanabe, M. Shiga, S. Watanabe, "Upper bounds for variational stochastic complexities of Bayesian networks,"
Proceedings of International Conference on Intelligent Data Engineering and Automated Learning(IDEAL2006), Burgos, Spain, pp. 139-146, 2006.

K. Watanabe, S. Watanabe, "Variational bayesian stochastic complexity of mixture models,"
Advances in Neural Information Processing Systems 18, pp. 1465-1472, The MIT Press, 2006.

K. Watanabe, S. Watanabe, "Variational bayesian algorithm and stochastic complexity for mixture models,"
Proceedings of International Conference on Neural Information Processing (ICONIP2005), Taipei, Taiwan, pp. 338-342, 2005.

K. Watanabe, S. Watanabe, "On variational bayes algorithms for exponential family mixtures,"
Proceedings of International Symposium on Nonlinear Theory and its Applications (NOLTA2005), Bruges, Belgium, pp. 393-396, 2005.

K. Watanabe, S. Watanabe, "Stochastic complexity for mixture of exponential families in variational bayes,"
Proceedings of the 16th International Conference on Algorithmic Learning Theory (ALT2005), Singapore, pp. 107-121, 2005.

T. Hosino,K. Watanabe, S. Watanabe, "Stochastic complexity of variational Bayesian hidden Markov models,"
Proceedings of 2005 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 1114-1119, 2005.

K. Watanabe, S. Watanabe, "Lower bounds of stochastic complexities in variational bayes learning of gaussian mixture models,"
Proceedings of IEEE International Conference on Cybernetics and Intelligent Systems, Singapore, pp. 99-104, 2004.

K. Watanabe, S. Watanabe, "Estimation of the data region using extreme-value distributions,"
Proceedings of the 15th International Conference on Algorithmic Learning Theory (ALT2004), Padova, Italy, pp. 206-220, 2004.

K. Watanabe, S. Watanabe, "Learning method of the data region based on extreme-value theory,"
Proceedings of International Symposium on Information Theory and its Applications (ISITA2004), Parma, Italy, pp. 87-92, 2004.

Book

Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama,
Variational Bayesian Learning Theory, Cambridge University Press, 2019.

Ph.D. Thesis

K. Watanabe, "Statistical Learning Theory of Variational Bayes,"
Tokyo Institute of Technology, 2006.

Other Presentations

Kazuho Watanabe, "Rate-distortion theoretic interpretation of Bayesian learning coefficients"
2020 ITA Workshop, San Diego, USA, Feb. 3, 2020.[Invited]

Masahiro Kobayashi, Kazuho Watanabe, "Unbiased Estimation Equation Under f-separable Extension of Squared and Itakura-Saito Distances,"
Data Science, Statistics and Visualization (DSSV), p.58, 13th, August, 2019 (poster).

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, "Rate-Distortion Function and Optimization of Probability Measure",
SITA Workshop, The 37th Symposium on Information Theory and its Applications (SITA2014), Unazuki, Toyama, Japan, Dec. 09-12, 2014.

Kazuho Watanabe, "Nonparametric Estimation of Latent Distributions in Mixture Models",
HIIT Seminar, Helsinki Institute for Information Technology, 5th, Oct, 2012.

Kazuho Watanabe, "Approximate Bayesian learning using Bregman divergence",
IMS Asia Pacific Rim Meetings (IMS-APRM), 4th, Jul, 2012.

Kazuho Watanabe, "Nonparametric estimation of mixture model and minimum divergence method",
The 6th Statistical Machine Learning Seminar, The Institute of Statistical Mathematics, 24th, Nov, 2011.

Atsushi Miyamoto, Kazuho Watanabe, Kazushi Ikeda, Masa-aki Sato, "Variational Bayes method for NIRS-DOT inverse problem and its phase transition",
the 20th Annual Meeting of Japanese Neural Network Society, Neuro2010, Kobe, 2010 (poster presentation).

Kazuho Watanabe, "Local Variational Approximation and Spike Rate Estimation,"
Workshop on the state-space analysis,
Yukawa Institute for Theoretical Physics, Kyoto University, 8-9th, Apr, 2010.

K. Watanabe, "Approximate Bayesian Estimation Methods and Their Applications,"
The 24th SIP Symposium, pp. 98-103, Kagoshima, Japan, Nov 2009 (tutorial).

K. Watanabe, "Stochastic complexity and variational approximation,"
The 3rd Mathematical Science Forum in Tokyo Tech, 2005, (poster and oral presentation).

K. Watanabe, S. Watanabe, "stochastic complexity of gaussian mixture in variational bayes,"
IEEE Tokyo Student Workshop,2005(poster presentation).

back