Takeru Matsuda

Takeru Matsuda, Ph.D.

Unit Leader, Statistical Mathematics Unit
takeru.matsuda [at] riken.jp

Research Overview

With recent advances in experimental technologies, large-scale and diverse brain data are now available. To extract more information from such brain data, we develop tailored statistical methods by translating the characteristics of data into the form of statistical models. We incorporate techniques from applied mathematics, such as numerical analysis and optimization, to develop efficient methods that are applicable to large-scale data. We also investigate the fundamental theory of statistics.

Main Research Field

Informatics

Related Research Fields

Interdisciplinary science and engineering 
Mathematical and physical sciences
Statistical science
Mathematical informatics

Keywords

Selected Publications

  1. Uehara, M., Matsuda, T. and Kim, J. K.
    Imputation estimators for unnormalized models with missing data
    23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
  2. Xu, W. and Matsuda, T.
    A Stein goodness-of-fit test for directional distributions
    23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
  3. Matsuda, T. and Hyvarinen, A.
    Estimation of non-normalized mixture models
    22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019).
  4. Matsuda, T. and Strawderman, W. E.
    Improved loss estimation for a normal mean matrix
    Journal of Multivariate Analysis 169, 300--311, 2019.
  5. Matsuda, T. and Komaki, F.
    Empirical Bayes matrix completion
    Computational Statistics & Data Analysis 137, 195--210, 2019.
  6. Maruyama, Y., Matsuda, T. and Ohnishi, T.
    Harmonic Bayesian prediction under alpha-divergence
    IEEE Transactions on Information Theory 65, 5352-5366, 2019.
  7. Matsuda, T. and Komaki, F.
    Multivariate time series decomposition into oscillation components
    Neural Computation 29, 2055--2075, 2017.
  8. Matsuda, T. and Komaki, F.
    Time series decomposition into oscillation components and phase estimation
    Neural Computation 29, 332--367, 2017.
  9. Matsuda, T., Kitajo, K., Yamaguchi, Y. and Komaki, F.
    A point process modeling approach for investigating the effect of online brain activity on perceptual switching
    NeuroImage 152, 50--59, 2017.
  10. Matsuda, T. and Komaki, F.
    Singular value shrinkage priors for Bayesian prediction
    Biometrika 102, 843--854, 2015.