Publications by Kenji Fukumizu

• Fukumizu, K. Introduction to Kernel Methods (in Japanese)
  Asakura Shoten. (Nov 2010) (Info in Japanese)
  

• Fukumizu, K., Kuriki, S., Takeuchi, K., and Akahira, M. Statitical Theory of Singular Models (in Japanese)
  (Frontiers of Statistical Science 7). Iwanami. (July 2004)
  

• Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu (2016) Convergence guarantees for kernel-based quadrature rules in misspecified settings
  arXiv:1605.07254 [stat.ML]
  

• Genki Kusano, Kenji Fukumizu and Yasuaki Hiraoka (2015) Persistence weighted Gaussian kernel for topological data analysis,
  arXiv:1601.01741 [math.AT]
  

• Momoko Hayamizu and Kenji Fukumizu (2015) On the existence of infinitely many universal tree-based networks,
  arXiv:1512.02402
  

• Momoko Hayamizu, Hiroshi Endo and Kenji Fukumizu (2015) A characterization of minimum spanning tree-like metric spaces,
  arXiv:1510.09155 [q-bio.QM]
  

• Momoko Hayamizu and Kenji Fukumizu (2015) On the minimum spanning tree-like metric spaces,
  arXiv:1505.06145 [math.CO]
  

Articles

• Variational Learning on Aggregate Outputs with Gaussian Processes,
  Ho Chung Law, Dino Sejdinovic, Ewan Cameron, Tim Lucas, Seth Flaxman, Katherine Battle, Kenji Fukumizu
  Advances in Neural Infromation Processing Systems 31 (NIPS 2018) paper

• Genki Kusano, Kenji Fukumizu, and Yasuaki Hiraoka (2018) Kernel method for persistence diagrams via kernel embedding and weight factor
  Journal of Machine Learning Research pdf

• Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur and Bernhard Schölkopf (2017),
  Kernel Mean Embedding of Distributions: A Review and Beyond,
  Foundations and Trends® in Machine Learning: Vol. 10: No. 1-2, pp 1-141. paper

• Wittawat Jitkrittum, Wenkai Xu, Zoltan Szabo, Kenji Fukumizu, Arthur Gretton (2017) A Linear-Time Kernel Goodness-of-Fit Test
  Advances in Neural Information Processing Systems 30 (NIPS 2017) web page .

• Song Liu, Akiko Takeda, Taiji Suzuki, Kenji Fukumizu (2017) Trimmed Density Ratio Estimation
  Advances in Neural Information Processing Systems 30 (NIPS 2017) web page .

• Ruriko Yoshida, Kenji Fukumizu, Chrysafis Vogiatzis (2017) Multilocus Phylogenetic Analysis with Gene Tree Clustering
  Annals of Operations Research link

• Song Liu, Kenji Fukumizu, and Taiji Suzuki (2017) Learning sparse structural changes in high-dimensional Markov networks
  Behaviormetrika, 1. doi:10.1007/s41237-017-0014-z

• Yu Nishiyama, Kenji Fukumizu (2016) Characteristic Kernels and Infinitely Divisible Distributions
  Journal of Machine Learning Research, 17(180):1--28. (link)

• Motonobu Kanagawa, Barath K. Sriperumbudur, Kenji Fukumizu. (2016) Convergence guarantees for kernel-based quadrature rules in misspecified settings
  Advances in Neural Information Processing Systems 30 link. arXiv version arXiv:1605.07254 [stat.ML]

• Tomoharu Iwata, Motonobu Kanagawa, Tsutomu Hirao, Kenji Fukumizu (2016) Unsupervised group matching with application to cross-lingual topic matching without alignment information
  Data Mining and Knowledge Discovery (online: 24 June, 2016) DOI: 10.1007/s10618-016-0470-1

• Krikamol Muandet, Bharath Sriperumbudur, Kenji Fukumzu, Arthur Gretton, Bernhard Scholkopf. (2016) Kernel Mean Shrinkage Estimators. Journal of Machine Learning Research, 17(48):1--41, 2016. (link)

• Song Liu, Taiji Suzuki, Raissa Relator, Jun Sese, Masashi Sugiyama and Kenji Fukumizu (2016) Support Consistency of Direct Sparse-Change Learning in Markov Networks, Annals of Statsitics, to appear.

• Momoko Hayamizu, Hiroshi Endo and Kenji Fukumizu (2016). A Characterization of Minimum Spanning Tree-like Metric Spaces. IEEE/ACM Transactions on Computational Biology and Bioinformatics, DOI: 10.1109/TCBB.2016.2550431
  

• Motonobu Kanagawa, Yu Nishiyama, Arthur Gretton, Kenji Fukumizu, Filtering with State-Observation Examples via Kernel Monte Carlo Filter
  Neural Computation, Vol. 28, No. 2: 382-444. (link)
  arXiv version arXiv:1312.4664 [stat.ML]
  

• Bernhard Scholkopf, Krikamol Muandet, Kenji Fukumizu, Stefan Harmeling, Jonas Peters, Computing functions of random variables via reproducing kernel Hilbert space representations.
  Statistics and Computing, June, 2015 link
  

• Md. Ashad Alam and Kenji Fukumizu. (2015) Higher-Order Regularized Kernel Canonical Correlation Analysis. Int. J. Patt. Recogn. Artif. Intell. 29, 1551005 [24 pages] DOI: 10.1142/S0218001415510052
  

• Somayeh Danafar, Kenji Fukumizu, Faustino Gomez: Kernel-Based Information Criterion.
  Computer and Information Science 8(1): 10-24 (2015) link
  

• Francesco Dinuzzo, Cheng Soon Ong, Kenji Fukumizu. Output Kernel Learning Methods. Regularization, Optimization, Kernels, and Support Vector Machines, CRC Press, 2014. (pdf)
  

• Alam, M.A. and K. Fukumizu, (2014). Hyperparameter selection in kernel principal component analysis.
  J. Compututer Science, 10: 1139-1150. link
  

• Kenji Fukumizu, Le Song, Arthur Gretton (2013) Kernel Bayes' Rule: Bayesian Inference with Positive Definite Kernels
  Journal of Machine Learning Research, vol.14, pp.3753＊3783, 2013. paper
  

• Shigeki Nakagome, Shuhei Mano and Kenji Fukumizu (2013) Kernel Approximate Bayesian Computation in Population Genetic Inferences
  Statistical Applications in Genetics and Molecular Biology, Volume 12, Issue 6, Pages 667--678, DOI: 10.1515/sagmb-2012-0050, arXiv
  

• Kenji Fukumizu and Chenlei Leng (2013) Gradient-based kernel dimension reduction for regression.
  Journal of the American Statistical Association, Volume 109, Issue 505, pages 359-370, 2014. paper, Matlab code
  

• Dino Sejdinovic, Bharath Sriperumbudur, Arthur Gretton, and Kenji Fukumizu (2013) Equivalence of distance-based and RKHS-based statistics in hypothesis testing.
  Annals of Statistics 41, Number 5, 2263-2702. paper,
  

• Song, L., Gretton, A., and Fukumizu, K. (2013) Kernel Embeddings of Conditional Distributions.
  IEEE Signal Processing Magazine 30(4), pp. 98-111. paper,
  

• K. Fukumizu, C. Leng (2012) Gradient-based kernel method for feature extraction and variable selection.
  Advances in Neural Information Processing Systems 25 (NIPS2012), pp.2123-2131. paper, supplemental
  

• K. Muandet, K. Fukumizu, F. Dinuzzo, B. Schoelkopf. (2012) Learning from Distributions via Support Measure Machines.
  Advances in Neural Information Processing Systems 25 (NIPS2012), pp.10-18.paper, supplemental.
  

• A. Gretton, B. Sriperumbudur, D. Sejdinovic, H. Strathmann, S. Balakrishnan, M. Pontil, K. Fukumizu (2012) Optimal kernel choice for large-scale two-sample tests.
  Advances in Neural Information Processing Systems 25 (NIPS2012), pp.1214-1222. paper, supplemental.
  

• B. Sriperumbudur, K. Fukumizu, A. Gretton, B. Schoelkopf, G. Lanckriet (2012) On the empirical estimation of integral probability metrics.
  Electronic Journal of Statistics 6, 1550-1599. paper,
  

• B. Sriperumbudur, K. Fukumizu, G. Lanckriet (2011) Learning in Hilbert vs. Banach Spaces: A Measure Embedding Viewpoint.
  Advances in Neural Information Processing Systems 24 (NIPS2011) paper, supplement (zip)
  

• K. Fukumizu, L. Song, A. Gretton (2011) Kernel Bayes' Rule.
  Advances in Neural Information Processing Systems 24 (NIPS2011) longer version
  

• Yuichi Shiraishi, Kenji Fukumizu, (2011) Statistical approaches to combining binary classifiers for multi-class classification, Neurocomputing, 74, (5), Pages 680-688. paper
  

• Bharath K. Sriperumbudur, Kenji Fukumizu, Gert R.G. Lanckriet (2011) Universality, Characteristic Kernels and RKHS Embedding of Measures ;(Jul2011.
  Journal of Machine Learning Research, 12 2389-2410. pdf
  

• Watanabe, Y. and Fukumizu, K. (2010) New graph polynomials from the Bethe approximation of the Ising partition function
  Combinatorics, Probability and Computing. Published online (June, 2010) pdf
  

• Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fukumizu, Bernhard Scholkopf, Gert R.G. Lanckriet. (2010) Hilbert Space Embeddings and Metrics on Probability Measures.
  Journal of Machine Learning Research. 11(Apr):1517-1561. pdf
  

• Sriperumbudur, B., K. Fukumizu, A. Gretton, G. Lanckriet and B. Scholkopf. Kernel Choice and Classifiability for RKHS Embeddings of Probability Distributions.
  Advances in Neural Information Processing Systems 22, 1750-1758, MIT Press (2010)
  pdf, suppl. Student Paper Award (Honorable Mention)

• Gretton, A., Z. Harchaoui, K. Fukumizu, B. SriperumbudurA Fast, Consistent Kernel Two-Sample Test. .
  Advances in Neural Information Processing Systems 22, 673-681, MIT Press (2010) pdf , suppl.
  

• Watanabe, Y. and K.Fukumizu. Graph Zeta Function in the Bethe Free Energy and Loopy Belief Propagation.
  Advances in Neural Information Processing Systems 22, 2017-2025, MIT Press (2010) pdf, suppl.
  

• Gretton, A., K. Fukumizu, and B.K. Sriperumbudur. (2009) Discussion of: Brownian distance covariance Annals of Applied Statistics, Volume 3, Number 4, 1285-1294. link
  

• Fukumizu, K. Exponential manifold by reproducing kernel Hilbert spaces.
  in Algebraic and Geometric mothods in statistics (P. Gibilisco, E. Riccomagno, M.-P .Rogantin, and H. Winn eds.) pp.291-306. Cambridge University Press. (2009). pdf
  

• Watanabe, Y. and K. Fukumizu. Loop series expansion with propagation diagrams. Journal of Physics A: Mathematical and Theoretical 42 (2009) 045001 (18pp) pdf file
  

• Fukumizu, K. Francis R. Bach and M. Jordan. Kernel dimension reduction in regression.
  The Annals of Statistics. 37(4), pp.1871-1905 (2009) pdf file
  

• Fukumizu, K., B.K. Sriperumbudur, A. Gretton and B. Scholkopf. Characteristic Kernels on Groups and Semigroups. Advances in Neural Information Processing Systems 21, pp.473-480, MIT Press (2009). pdf file
  

• Fukumizu, K., A. Gretton, X. Sun, and B. Scholkopf: Kernel Measures of Conditional Dependence.
  Advances in Neural Information Processing Systems 20, 489-496, MIT Press (2008). pdf file
  

• Arthur Gretton, Kenji Fukumizu, Choon Hui Teo, Le Song, Bernhard Scholkopf, Alex Smola. A Kernel Statistical Test of Independence.
  Advances in Neural Information Processing Systems 20, 585-592, MIT Press (2008). pdf file

• K. Fukumizu. Statistical estimation with positive definite kernels. in Statistical Science in the 21th Century III (G. Kitagawa and A. Takemura eds.) pp. 257-290. (2008) University of Tokyo Press. (in Japanese)
  

• Shiraishi, Y. and K. Fukumizu. Game Theoretical Combination of Binary Classifiers for Multi-Class Classification.
  IEICE Transactions on Information and Systems Vol.J91-D No.6 pp.1528-1537 (2008). (in Japanese)
  

• Fukumizu, K., F. R. Bach and A. Gretton: Statistical Consistency of Kernel Canonical Correlation Analysis.
  Journal of Machine Learning Research 8, 361-383 (2007). pdf file
  

• Tanabe, A., Fukumizu, K. Oba, S., Takenouchi, T., and Ishii, S. "Parameter Estimation for von Mises-Fisher distributions",
  Computational Statistics. Vol.22, No.1: 145-157 (2007).

• Cuturi, M. and K. Fukumizu. Kernels on Structured Objects Through Nested Histograms
  Advances in Neural Information Processing Systems 19, pp.329--336, MIT Press (2007). pdf file

• Fukumizu, K.Statitical Theory of Active learning (in Japanese)
  Theory and Practice of Learning Systems, Chapter 5. Morikita-Shuppan. (July 2005)
  

• Marco Cuturi, Kenji Fukumizu, and Jean-Philippe Vert. "Semigroup Kernels on Measures",
  Journal of Machine Learning Research, vol.6, pp.1169-1198 (2005). pdf file
  

• Fukumizu, K. "Singularity of neuro-manifolds and infinite degree of local freedom", (in Japanese)
  Suri Kagaku (Mathematical Sciences), March 2005 pp.25-36, Science-Sya.

• Watanabe, S., Fukumizu, K., Hagiwara, K., and Amari, S. "Learning Theory of Singular Models" (in Japanese),
  IEICE VOL.J88-D2 No.2, pp.159-169 (February 2005)

• Ikeda-Fukazawa, T., Fukumizu, K., Kawamura, K., Aoki, S., Nakazawa, T., and Hondoh, T.
  "Effects of molecular diffusion on trapped gas composition in polar ice cores".
  Earth and Planetary Science Letters, Vol.229, Issues 3-4, 15 January 2005, Pages 183-192.

• Fukumizu, K., Bach, F.R., and Jordan, M.I. "Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces",
  Journal of Machine Learning Research. 5(Jan):73-99, 2004. pdf , gzipped ps .

• Fukumizu, K., Bach, F.R., and Jordan, M.I. "Kernel Dimensionality Reduction for Supervised Learning",
  Advances in Neural Information Processing Systems 16, pp.81-88 (2004). pdf file

• Fukumizu, K. and Kuriki, S. "Statistical inference in singular models -- an approach by tangent cone --", (in Japanese)
  Journal of Japan Neural Network Society. 10(4):201-210, 2003. pdf .

• Fukumizu, K. and Akaho, S. and Amari, S. "Critical lines in symmetry of mixture models and its application to component splitting",
  Advances in Neural Information Processing Systems 15, pp.857-864 (2003). gzipped ps (251k), pdf

• Fukumizu, K. "Likelihood Ratio of Unidentifiable Models and Multilayer Neural Networks",
  The Annals of Statistics, Vol.31, No.3. pp.833-851. (2003, June). pdf file

• Fukumizu, K. "Geometry of neural networks: Natural gradient for learning",
  in F.Moss & S.Gielen (eds.) Handbook of Biological Physics, vol.4: Neuro-informatics and Neural Modelling. pp.731-769. Elsevier (2001).

• Fukumizu, K. and Amari, S. "Local Minima and Plateaus in Hierarchical Structures of Multilayer Perceptrons",
  Neural Networks, Vol.13, No.3, pp.317-327 (2000). (zipped ps file, pdf file)

• Amari, S., Park, H., and Fukumizu, K. "Adaptive method of realizing natural gradient learning for multilayer perceptrons",
  Neural Computation, Vol.12(6) pp.1399-1409 (2000). ( zipped ps file, pdf file)

• Park, H., Amari, S., and Fukumizu, K. "Adaptive natural gradient learning algorithms for various stochastic models",
  Neural Networks, 13(7) pp.755-764 (2000). ( zipped ps file, pdf file)

• Fukumizu, K. "Dynamics of Batch Learning in Multilayer Neural Networks - Overrealizability and Overtraining -",
  submitted to Neural Networks. (1998). (zipped ps file, pdf file)

• Fukumizu, K. "Statistical Active Learning in Multilayer Perceptrons",
  IEEE Transactions on Neural Networks, Vol.11, No.1, pp.17-26 (2000). ( zipped ps file, pdf file)

• Watanabe, S and Fukumizu, K. "Probabilistic design",
  in Cornelius T. Leondes (ed.), NEURAL NETWORK SYSTEMS TECHNIQUES AND APPLICATIONS Series, Vol.1. Academic Press. (1997).

• Fukumizu, K. "Active learning in neural networks",
  Journal of IPSJ, Vol.38, No.7, pp.569-574 (July 1997) (in Japanese)

• Fukumizu, K. "A regularity condition of the information matrix of a multilayer perceptron network", Neural Networks, Vol.9, No.5, pp.871-879 (1996).

• Fukumizu, K. and Watanabe, S. "Optimal training data and predictive error of polynomial approximation",
  Tran. IEICE, Vol.J79-A, No.5, pp.1100-1108 (1996) (in Japanese).

• Ishii, S., Watanabe, S. and Fukumizu, K.
  "A network of chaotic elements for information processing", Neural Networks, Vol.9, No.1, pp.25-40 (1996).

• Watanabe, S. and Fukumizu, K. "Probabilistic design of layered neural networks based on their unified framework",
  IEEE Transactions on Neural Networks, Vol.6, No.3, pp.691-702, (1995).

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
S. Yokoi, S. Kobayashi, K. Fukumizu, J. Suzuki and K. Inui, has been accepted in EMNLP 2018.
• Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
  Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki and Kentaro Inui
  2018 Conference on Empirical Methods in Natural Language Processing. (arXiv version)

• Takafumi Kajihara, Keisuke Yamazaki, Motonobu Kanagawa, Kenji Fukumizu.
  Kernel Recursive ABC: Point Estimation with Intractable Likelihood.
  In Proc. 35th International Conference on Machine Learning (ICML 2018). paper

• Post Selection Inference with Kernels
  by Makoto Yamada, Yuta Umezu, Kenji Fukumizu, and Ichiro Takeuchi.
  Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in PMLR 84:152-160 paper

• Yao-Hung Hubert Tsai, Denny Wu, Makoto Yamada, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
  Selecting the Best in GANs Family: a Post Selection Inference Framework
  6th International Conference on Learning Representations Workshop Track (ICLR 2018) (openreview)

• Liu, S., Suzuki, T., Sugiyama, M. and Fukumizu, K. (2016)
  Structure Learning of Partitioned Markov Networks,
  Proceedings of The 33rd International Conference on Machine Learning (ICML 2016), 439-448 (paper)

• Kusano, G., Hiraoka, Y. and Fukumizu, K. (2016)
  Persistence weighted Gaussian kernel for topological data analysis,
  Proceedings of The 33rd International Conference on Machine Learning, pp. 2004--2013 (paper)

• Kazuo Hara, Ikumi Suzuki, Kei Kobayashi, and Kenji Fukumizu. 2015.
  Reducing Hubness: A Cause of Vulnerability in Recommender Systems.
  In Proc. 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '15). ACM, New York, NY, USA, 815-818. DOI=http://dx.doi.org/10.1145/2766462.2767823

• K. Hara, I. Suzuki, M. Shimbo, and K. Kobayashi, K. Fukumizu, and M. Radomanovic. (2015) Localized Centering: Reducing Hubness in Large-Sample Data. Proc. AAAI-2015

• Motonobu Kanagawa and Kenji Fukumizu (2014)
  Recovering Distributions from Gaussian RKHS Embeddings,
  Proc. 17th International Conference on Artificial Intelligence and Statistics (AISTATS 2014), 457-465. (paper)

• M. Kanagawa, Y. Nishiyama, A. Gretton, and K. Fukumizu. (2014) Monte Carlo Filtering using Kernel Embedding of Distributions. Proc. AAAI-2014, pages 1897-1903. (pdf)

• Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur, Arthur Gretton, Bernhard Schoelkopf. (2014) Kernel Mean Estimation and Stein Effect.
  JMLR W&CP volume 32 (1) Proc. 31st International Conference on Machine Learning (ICML 2014), pp.10-18, 2014. Paper

• Motonobu Kanagawa and Kenji Fukumizu (2014) Recovering Distributions from Gaussian RKHS Embeddings.
  Proc. 17th International Conference on Artificial Intelligence and Statistics (AISTATS 2014), pp457-465, 2014. Paper

• I. Suzuki, K. Hara, M. Shimbo, M. Saerens and K. Fukumizu (2013) Centering Similarity Measures to Reduce Hubs.
  Proceedings of the 2013 Conference On Empirical Methods In Natural Language Processing (EMNLP2013), pp.613-623
  

• Francesco Dinuzzo, Cheng Soon Ong, Kenji Fukumizu. (2013) Output Kernel Learning Methods.
  Regularization, Optimization, Kernel Methods and Support Vector Machines: theory and applications (ROCKS2013). extended abstract
  

• Yu Nishiyama, Abdeslam Boularias, Arthur Gretton, Kenji Fukumizu. (2012) Hilbert Space Embeddings of POMDPs. Proc. Conference on Uncertainty in Artificial Intelligence (UAI2012). Paper Supplements
  

• Dino Sejdinovic, Arthur Gretton, Bharath Sriperumbudur, Kenji Fukumizu. (2012) Hypothesis testing using pairwise distances and associated kernels. Proc. 29th International Conference on Machine Learning (ICML2012). pdf file
  

• Francesco Dinuzzo, Kenji Fukumizu. (2011) Learning low-rank output kernels. Proc. 3rd Asian Conference on Machine Learning. pdf file
  

• Fukumizu, K. Statistical Inference with Reproducing Kernels. (invited) 8th International ISAAC Congress (Moscow) Aug 2011. pdf

• Sriperumbudur, B., Fukumizu, K., Gretton, A., Schoelkopf, B., and Lanckriet, G. (2010). Non-parametric estimation of integral probability metrics. The IEEE International Symposium on Information Theory.
• Bharath Sriperumbudur, Kenji Fukumizu, Gert Lanckriet. (2010) On the relation between universality, characteristic kernels and RKHS embedding of measures.
  Proc. 13th Intern．Conf. Artificial Intelligence and Statistics (AISTATS2010) 9:773-78. pdf
  

• Song, L., J. Huang, A. Smola and K. Fukumizu. (2009) Hilbert Space Embeddings of Conditional Distributions with Applications to Dynamical Systems.
  Proc. 26th Intern．Conf. Machine Learning (ICML2009), 961-968. pdf file
  

• Bharath Sriperumbudur, Arthur Gretton, Kenji Fukumizu, Gert Lanckriet and Bernhard Scholkopf.
  Injective Hilbert Space Embeddings of Probability Measures.
  Proceedings of the 21st Annual Conference on Learning Theory (COLT 2008) , pp.111-122 2008 pdf file
  

• Xiaohai Sun, Dominik Janzing, Bernhard Scholkopf and Kenji Fukumizu: A kernel-based causal learning algorithm.
  Proc. 24th Annual International Conference on Machine Learning (ICML2007), 855-862 (2007)pdf file

• Hagiwara, K. and Fukumizu, K. "Over-fitting behavior of Gaussian unit under Gaussian noise", Inter. Joint Conf. Neural Networks, 2004, Budapest.
  pdf file

• Fukumizu, K. "A Kernel Method for hierarchical and non-hierachical clustering", Science of Modeling. Dec., 2003.
  Summary (pdf) (corrected)

• Fukumizu, K., F.Bach, and M.Jordan. "Kernel Dimension Reduction for Regression", Learning Workshop at Snowbird. Apr. 1-4, 2003.
  Summary (ps), slides

• Fukumizu, K. "Asymptotic Theory of Locally Conic Models and its Application to Multilayer Neural Networks",
  Knowledge-Based Intelligent Information Engineering Systems & Allied Technologies (KES'2001), part 2. pp.1570-1574. IOS Press (2001).

• Fukumizu, K. "Geometry of Neural Networks and Models with Singularities ",
  in AIP Conference Proceedings 553: DISORDERED AND COMPLEX SYSTEMS. pp.117-122. American Institute of Physics (2001).

• Fukumizu, K. "Generalization error of linear neural networks in unidentifiable cases",
  O.Watanabe and T.Yokomori (eds.) Lecture Notes in Artificial Intelligence 1720, Algorithmic Learning Theory (Proceedings of the 10th International Conference on Algorithmic Learning Theory (ALT'99)), pp.51-62. Springer-Verlag: Berlin, 1999.

• Fukumizu, K. and Amari, S. "Local Minima and Plateaus in Multilayer Neural Networks",
  Proceedings of 9th International Conference on Artificaial Neural Networks (ICANN'99), pp.597-602 (1999) (zipped ps file, pdf file).

• Fukumizu, K. "Learning in neural networks and an integrable system", in Applied Mathematics of Discrete Integrable Systems, RIMS kokyuroku 1098, pp.23-41 (1999) (zipped ps file, pdf file)

• Fukumizu, K. "Effect of Batch Learning in Multilayer Neural Networks", Proc. 5th International Conference on Neural Information Processing (ICONIP'98), pp.67-70 (1998)
  (zipped ps file, pdf file)

• Fukumizu, K. "Dynamics of Batch Learning in Multilayer Neural Networks", Proceedings of 8th International Conference on Artificaial Neural Networks (ICANN'98), pp.189-194 (1998)
  (zipped ps file, pdf file)

• Fukumizu, K. "Generalization error of linear neural networks",
  Inverse Problems and Applications (4), The Institute of Statistical Mathematics Cooperative Research Report 108, pp.7-18 (1998) ( zipped ps file)

• Fukumizu, K. "Special statistical properties of neural network learning",
  In Proceedings of 1997 International Symposium on Nonlinear Theory and Its Applications (NOLTA'97), pp.747-750 (1997). ( zipped ps file, pdf file)

• Fukumizu, K. "Active learning in multilayer perceptrons",
  In David~S. Touretzky, Michael~C. Mozer, and Michael~E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pp.295-301. MIT Press, 1996. ( zipped ps file, pdf file)

• Fukumizu, K. and Watanabe, S. "Error estimation and learning data arrangement for neural networks",
  Proceedings of IEEE International Conference on Neural Networks, Vol.2, pp.777-780, June 1994.

• Ishii, S., Fukumizu, K., and Sumio Watanabe. "Globally coupled map model for information processing",
  Proceedings of International Symposium on Nonlinear Theory and Its Applications (NOLTA'93), pp.1157-1160, 1993.

• Ishii, S., Fukumizu, K., and Watanabe, S. "Associative memory using saptiotemporal chaos",
  Proceedings of 1993 Joint Conference on Neural Networks, Vol.3, pp.2638-2641, October 1993.

• Fukumizu, K. and Watanabe, S., "Probability density estimation by regularization method",
  Proceedings of 1993 Joint Conference on Neural Networks, Vol.2, pp.1727-1730, October 1993.

• Watanabe, S. and Fukumizu, K., "The unified neural network theory and its applicatons to new models",
  Proceedings of the International Joint Conference on Neural Networks (Beijing)}, pp.II 381-386, November 1992.

• Watanabe, S and Fukumizu, K. "The unified neural network theory and proposal of new models",
  Proceedings of the 2nd International conference on Fuzzy Logic and Neural Networks, pp.725-728, July 1992.

• Fukumizu, K., Kitagawa, H., and Yoneyama, M., " Active noise control with indoor positioning system",
  Second International Congress on Recent Developments in Air- and Structure-borne Sound and Vibration, Vol.1, pp.329-336, March 1992.

• Fukumizu, K., F. R. Bach and M. I. Jordan. Kernel dimension reduction in regression.
  Technical Report 715, Department of Statistics, University of California, Berkeley, 2006. pdf file
  

• Kenji Fukumizu, Francis R. Bach and Arthur Gretton. "Consistency of Kernel Canonical Correlation Analysis",
  Research Memorandum No.942, Institute of Statistical Mathematics. (June 2005). pdf file
  

• Marco Cuturi, Kenji Fukumizu, and Jean-Philippe Vert. "Semigroup Kernels on Measures",
  Research Memorandum No.933, Institute of Statistical Mathematics. (Jan 2005). pdf file
  

• Fukumizu, K, Hagiwara, K. "A general upper bound of likelihood ratio for regression",
  Research Memorandum No.887, Institute of Statistical Mathematics. 2003. pdf file

• Fukumizu, K., Bach, F.R., and Jordan, M.I. "Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces",
  Technical Report No.641, UC Berkeley, Dept. of Statsitics. 2003. download

• Fukumizu, K, Hagiwara, K. "A general upper bound of likelihood ratio in binary regression",
  Research Memorandum No.858, Institute of Statistical Mathematics. 2002. pdf file

• Fukumizu, K, Akaho, S, and Amari, S. "Critical Lines in Symmetry of Mixture Models and its Application to Component Splitting",
  Research Memorandum No.844, Institute of Statistical Mathematics. 2002. pdf file

• Fukumizu, K. "Likelihood Ratio of Unidentifiable Models and Multilayer Neural Networks",
  Research Memorandum No.780, The Institute of Statistical Mathematics. 2001. pdf file

Conference papers in Japanese and others

• 田辺昭博，福水健次，大羽成征，石井信．混合von Mises-Fisher分布に対する変分法的ベイズ推定．
  2004年 情報論的学習理論ワークショップ, pp46-51. pdfファイル．（2004年11月）

• 福水健次．階層的なモデルにおける学習の目的関数の大域的性質．
  日本神経回路学会時限研究会「神経回路網の特異構造と学習理論《 2004年11月 予稿psファイル（訂正版）, 講演スライド

• 福水健次, Francis R. Bach, Michael I. Jordan． カーネルヒルベルト空間を用いた回帰問題における特徴抽出．
  2003年 情報論的学習理論ワークショップ. pp.241-246.pdfファイル.（2003年11月）

• 萩原克幸，福水健次．Over-fitting of a Gaussian unit under Gaussian noise．
  2003年 情報論的学習理論ワークショップ. pp.229-234. （2003年11月）

• 福水健次．再生核ヒルベルト空間を用いた回帰問題における次元削減法．（特別講演）
  2003年 日本数学会秋季総合分科会 . 統計数学分科会講演アブストラクト pp.137-150., 講演スライド

• 福水健次, 栗木哲． 特異モデルにおける統計的推測. （チュートリアル講演）
  電子情報通信学会技術研究報告, NC 2003-27, pp.31-36, 7月 2003.pdfファイル

• 福水健次．局所錐型モデルの漸近理論とそのニューラルネットへの応用．
  2001年情報論的学習理論ワークショップ予稿集. pdf ファイル

• 福水健次．識別上能性を持つモデルの尤度比の漸近論．
  統計数理セミナー　2001/04/18. 講演ＯＨＰ

• 福水健次．ニューラルネットの推定理論 ― モデルの対称性と識別上能性 ―．（招待講演）
  応用統計学会・日本計量生物学会2001年度合同年次大会 予稿集 pp.25-36. pdf ファイル 講演ＯＨＰ

• Fukumizu, K. "Statistical analysis of unidentifiable models and its application to multilayer neural networks",
  Bernoulli-RIKEN BSI 2000 Symposium on Neural Networks and Learning: Satellite Workshop. Oct. 2000. (pdf file)

• 福水健次． ニューラルネットワークの数理統計学．
  YSGサマーセミナー Sep. 2000. 講演ＯＨＰ

• 福水健次． 錐型の特異点を持つモデルにおける最尤推定量の漸近的挙動．
  科研費シンポジウム　　　「統計的推測理論とその応用　―正則から非正則へ―《 講演論文集 2000. (pdf file)

• 福水健次．学習と幾何学．
  慶應サイエンス&テクノロジーシンポジウム2000　「データサイエンス《シンポジウム． 2000年７月． 講演ＯＨＰ

• 福水健次． 識別上能性を持つモデルにおける最尤推定量の挙動．
  科研費シンポジウム「探索的データ解析法と計算集約型統計手法《 講演論文集 1999. ( ps file, pdf file)

• 福水健次, 甘利俊一． 三層ニューラルネットワークのローカルミニマ．
  日本神経回路学会第9回全国大会講演論文集, pp.169-170, 1999. (Zipped ps file, 61k, pdf file, 203k.)

• 福水健次． 階層型モデルの最尤推定の汎化誤差
  １９９９年情報論的学習理論ワークショップ予稿集 (IBIS'99), pp.221-226, 1999.
  ( ps file, 372k, pdf file, 647k)

• 福水健次. 可積分系によるニューラルネットワークの学習の解析
  数理解析研究所講究録1098「離散可積分系の応用数理《, pp.23-41. 1999, 4月.

• 福水健次． 多層ニューラルネットワークのバッチ学習における過学習の 存在
  １９９８年情報論的学習理論ワークショップ予稿集(IBIS'98), pp.49-52, 1998.
  ( zipped ps file, pdf file>)

• 福水健次． 多層ニューラルネットワークの特殊な統計的性質．
  日本神経回路学会第8回全国大会講演論文集, 11月 1997.

• 福水健次． 特異なFisher情報行列を持つある非線形モデルの最尤推定の期待尤度 .
  統計数理研究所「逆問題とその周辺（３）《 統計数理研究所共同研究レポート94, pp.77-87, 1997.

• 福水健次． 特異なFisher情報行列を持つ線形ニューラルネットワークの汎化誤差.
  電子情報通信学会技術研究報告, NC 96-3, pp.17-24, 5月 1996.

• 福水健次． 能動学習 - 最適な質問の効果と問題点 -.
  日本神経回路学会第7回全国大会講演論文集, pp.153-157, 9月 1996.

• 福水健次． 多層パーセプトロンの能動学習とFisher情報行列.
  日本神経回路学会第6回全国大会講演論文集, pp.52-53, 10月 1995.

• 福水健次, 渡辺澄夫． 関数近似問題における最適学習設計と予測誤差.
  電子情報通信学会技術研究報告, NC 94-98, pp.173-180, 3月 1995.

• 福水健次, 渡辺澄夫． 多層パーセプトロンのFisher情報行列の正定値性について.
  電子情報通信学会技術研究報告, NC 94-33, pp.7-14, 10月 1994.

• 福水健次, 渡辺澄夫． ニューラルネットワークの適応型学習戦略.
  日本神経回路学会第5回全国大会, pp.90-91, 11月 1994.

• 福水健次, 渡辺澄夫． ニューラルネットワークの推定誤差の解析と学習データ最適化手法.
  電子情報通信学会技術研究報告, NC 93-126, pp.107-114, 3月 1994.

• 石井信, 福水健次, 渡辺澄夫． 大自由度カオスを用いた連想記憶.
  電子情報通信学会技術研究報告, 第NLP 92-94, pp.23-30, 1993.

• 石井信, 福水健次, 渡辺澄夫． 大域結合写像を用いた連想記憶.
  日本神経回路学会第4回全国大会講演論文集, pp.56-57, 7月 1993.

• 福水健次, 渡辺澄夫． Bayes事後確率の学習における推定誤差の解析.
  日本神経回路学会第4回全国大会講演論文集, pp.29-30, 7月 1993.

• 福水健次, 渡辺澄夫． 関数空間上のBayes推定による確率密度関数の決定法.
  日本神経回路学会第3回全国大会講演論文集, pp.72-73, 12月 1992.

• 福水健次, 渡辺澄夫． 統計的推論を実現するニューラルネットワークモデル.
  電子情報通信学会全国大会秋季大会, 第6巻, p.30, 1992.

• 福水健次, 渡辺澄夫． 統計的推論を実現するニューラルネットワークとそのパター ン認識への応用.
  電子情報通信学会技術研究報告, NC 92-36, pp.83-90, July 1992.

• 福水健次, 渡辺澄夫． 統計的推論を実現するニューラルネットワーク.
  電子情報通信学会技術研究報告, NC 91-123, pp.187-194, 3月 1992.

• 渡辺澄夫, 福水健次． ニューラルネットワークの統一理論と新しいモデルの提案.
  電子情報通信学会技術研究報告, NC 91-122, pp.179-186, 3月 1992.

  ---

  Back to Fukumizu's home page
  Back to Top page of Institute of Mathematical Statistics

  ---