LAB LOGA page on LabLog, a review site (not the lab's official page)
Learning Mathematical Informatics Lab (Yamanishi Lab)
Machine-translated · View original
A lab that finds the knowledge hidden deep in data through machine learning theory and data analysis.
AboutAbout the lab
Learning is a strategy for compressing data into its shortest form
The Learning Mathematical Informatics Lab studies how much knowledge computers can acquire from large amounts of data.
On the theoretical side, the lab works on information-theoretic learning theory, which is based on information theory and statistics.
On the practical side, it uses data mining to extract the knowledge buried deep in data, along with how that knowledge changes.
The lab also works on applications to real-world data in fields such as healthcare, transportation, marketing, and education.
Key terms
- MDL principle
- A basic principle of information theory holding that the best explanation is the one that describes the data most concisely
- Data mining
- Techniques for digging out useful rules and knowledge from large amounts of data
- Change detection
- Finding the points in a data stream where its behavior starts to differ from before, as well as signs of such a change
NewsLab news
Paper on normalized maximum likelihood code length for continuous variables accepted to IEEE Transactions on Information Theory
Paper on online MDP learning accepted to ICML 2026
Paper on causal inference with confounders accepted to ECML-PKDD 2026
Paper on normalized maximum likelihood codes on Riemannian manifolds accepted to IEEE Transactions on Information Theory
Prof. Yamanishi receives the Telecom Interdisciplinary Research Award (Special Commendation)
ResearchResearch themes
The lab studies, with mathematical models at the center, how computers can acquire useful knowledge from large amounts of data. Its work rests on two pillars: information-theoretic learning theory, the theoretical side of machine learning, and data mining, the practical side.
*Illustrative imageInformation-Theoretic Learning Theory
The lab tackles the question "How far can a machine learn?" from the perspectives of information theory and statistics. Centered on the MDL principle, it derives algorithms for a wide range of learning problems, including model selection, change detection, and online learning, in a unified way.
*Illustrative imageFoundations of Data Mining
The lab studies techniques for finding knowledge in large amounts of data, such as anomaly detection, change detection, and network mining. It extracts the latent knowledge buried deep in data and, from how that knowledge changes, aims at early detection of anomalies and of signs that precede them.
*Illustrative imageApplications of Data Mining
The lab applies the above techniques to complex real-world data. Together with experts in each field, it analyzes data in areas such as healthcare (predicting glaucoma progression), traffic risk mining, marketing, social network analysis, and educational data analysis.
MembersFaculty
The members of the Learning Mathematical Informatics Lab consist of faculty, visiting researchers, doctoral and master's students, and secretaries.As of 2026
- ProfessorYamanishi KenjiPublications ↗
- ProfessorTaiji SuzukiPublications ↗
- LecturerRyohei HisanoPublications ↗
- Assistant ProfessorTaira Tsuchiya
- Project Assistant ProfessorRyoma Kondo
VoicesStudent voices
Compiled from answers by students who were in the lab. Ratings and reviews reflect individual students' experiences, not the lab's official views.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
On a 4-point scale, ● marks where students' answers fall
Who is this lab for?
What's great about this lab?
What did you learn after joining?
What's the vibe, and what is the professor like?
Where do graduates go?
RelatedLabs similar to Learning Mathematical Informatics Lab (Yamanishi Lab)
Statistical Informatics LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsFundamental theory of statistics; statistical modeling and d…
Mathematical Data Science LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsTheory and Applications of Mathematical Optimization and Mat…
Sadakane-Ito Lab (Mathematical Informatics Lab 2)Faculty of Engineering, Department of Mathematical Engineering and Information PhysicsAlgorithms for big data, succinct data structures, machine l…
Mathematical Bioinformatics LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsMathematical modeling of information processing mechanisms i…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “CERN Server 03” Florian Hirzinger - www.fh-ap.com / CC BY-SA 3.0 (cropped)
- Information-Theoretic Learning Theory: “Mandel bd” Adam majewski / Public domain (cropped)
- Foundations of Data Mining: “Ba model 1000nodes” Keiono / CC BY 3.0 (cropped)
- Applications of Data Mining: “Fundus photograph Retina OS” Ktkvtsh / CC BY-SA 4.0 (cropped)
- Related lab (統計情報学研究室): “Beta distribution for 3 different prior probability functions - J. Rodal” Dr. J. Rodal / CC BY-SA 3.0 (cropped)
- Related lab (数理データ科学研究室): “Rosenbrock function 2” RokerHRO / Public domain (cropped)
- Related lab (定兼・伊藤研究室
（数理情報第2研究室） ): “TSP Deutschland 3” The original uploader was Kapitän Nemo at German Wikipedia. / Public domain (cropped) - Related lab (数理生命情報学研究室): “Mouse Embryo Cerebellum ( )” NIH Image Gallery from Bethesda, Maryland, USA / Public domain (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.