If you made any changes in Pure these will be visible here soon.

Fingerprint Dive into the research topics where Junnichi Takeuchi is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

Exponential Family Mathematics
Factorization Engineering & Materials Science
Regret Mathematics
Supervised learning Engineering & Materials Science
Maximum likelihood Engineering & Materials Science
Data mining Engineering & Materials Science
Glossaries Engineering & Materials Science
Intrusion detection Engineering & Materials Science

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output 1993 2019

  • 922 Citations
  • 11 h-Index
  • 34 Conference contribution
  • 14 Article
  • 3 Conference article
  • 1 Paper

Asymptotic Behavior of Typical Sets and the Smallest High Probability Set

Eto, M., Kawakita, M. & Takeuchi, J., Mar 8 2019, Proceedings of 2018 International Symposium on Information Theory and Its Applications, ISITA 2018. Institute of Electrical and Electronics Engineers Inc., p. 717-721 5 p. 8664327. (Proceedings of 2018 International Symposium on Information Theory and Its Applications, ISITA 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Entropy

Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families

Miyamoto, K., Barron, A. R. & Takeuchi, J., Jul 2019, 2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 1442-1446 5 p. 8849350. (IEEE International Symposium on Information Theory - Proceedings; vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Data description
Exponential Family
Bundle
Estimator
Regret
1 Citation (Scopus)

A unified global convergence analysis of multiplicative update rules for nonnegative matrix factorization

Takahashi, N., Katayama, J., Seki, M. & Takeuchi, J., Sep 1 2018, In : Computational Optimization and Applications. 71, 1, p. 221-250 30 p.

Research output: Contribution to journalArticle

Non-negative Matrix Factorization
Global Analysis
Factorization
Convergence Analysis
Global Convergence

Information geometry of the family of Markov kernels defined by a context tree

Takeuchi, J. & Nagaoka, H., Jan 31 2018, 2017 IEEE Information Theory Workshop, ITW 2017. Institute of Electrical and Electronics Engineers Inc., Vol. 2018-January. p. 429-433 5 p.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Information Geometry
kernel
Geometry
Exponential Family
Model
1 Citation (Scopus)

A note on model selection for small sample regression

Kawakita, M. & Takeuchi, J., Nov 1 2017, In : Machine Learning. 106, 11, p. 1839-1862 24 p.

Research output: Contribution to journalArticle

Experiments