LAB LOGA page on LabLog, a review site (not the lab's official page)
〈Bayesian Statistics / Uncertainty Quantification〉
Machine-translated · View original
A lab that uses Bayesian statistics to understand physical phenomena from measurement data without ambiguity.
AboutAbout the lab
Interdisciplinary statistics that connects the ideal and the real.
Tokuda Lab works to establish guiding principles for understanding all kinds of physical phenomena unambiguously, based on data.
Combining mathematical modeling with statistical inference, the lab studies methods for comparing measurement data against models and selecting the model that best fits reality.
The foundation is Bayesian statistics, and the lab also conducts joint research with researchers in various sciences and in industry.
On the lab's website, it is introduced under the name "Tokuda Lab."
Key terms
- Bayesian statistics
- A statistical framework that expresses the plausibility of each model given the data as a probability. It is used to compare models with one another
- Mathematical modeling
- A method of representing measurement data with simple equations in order to understand the universal and the individual aspects of a phenomenon separately
- Uncertainty quantification
- An approach that expresses the magnitude of the uncertainty in data and models numerically. Abbreviated as UQ
- Band structure
- A representation of the energy states of electrons in a solid, which are unique to each material
NewsLab news
Opened a FAQ page for undergraduate students
Joined the QST quantum materials and information measurement project
ResearchResearch themes
With mathematical modeling and statistical inference as its two driving wheels, the lab aims to establish guiding principles (modeling principles) for understanding all kinds of physical phenomena without ambiguity. It tackles three challenges, namely model uncertainty, the effect of observation noise, and the effect of model misspecification, using tools such as Bayesian uncertainty quantification, from both theoretical and empirical sides.
*Illustrative imageComparing Which Model Is Valid Using Probabilities
A model captures the essence of a phenomenon, but what is essential is not self-evident. The lab uses Bayesian statistics to express the plausibility of each model given the data as a probability, and has demonstrated its usefulness in model selection in condensed matter physics, such as for velocity distribution functions and band structures.
*Illustrative imageThe Effect of Observation Noise
Measurement data always contain observation noise, and the larger the noise, the more uncertain the estimated parameters become. The lab has developed a method to estimate the magnitude of the noise (its variance) and the appropriate model simultaneously, and is also pursuing research on the asymptotic theory of Bayesian estimation.
*Illustrative imageDealing with Model Misspecification
A model is only an approximation of the truth, and there is always a discrepancy between a model and measurement data. The lab collectively calls discrepancies other than random observation noise "model misspecification," and is working on systematic ways to deal with it and on new theory to justify those methods.
*Illustrative imageEmpirical Research Resolving a Debate in Solid-State Physics
Observations by angle-resolved photoemission spectroscopy (ARPES) have long been the subject of debate over whether Dirac electrons, which behave like massless particles, have mass. In collaborative research, the lab proposed a method for analyzing ARPES data based on Bayesian statistics and applied it to TlBi(S,Se)2, contributing to determining the mass.
MembersFaculty
Tokuda Lab members consist of faculty, a part-time lecturer, technical staff, and master's and undergraduate students.As of 2026
- Associate ProfessorSatoru Tokuda
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to 〈Bayesian Statistics / Uncertainty Quantification〉
Bayesian Statistics and Uncertainty Quantification Lab (Satoru Tokuda)Institute of Mathematics for Industry, Division of Industrial Mathematical Statistics ResearchUncertainty quantification and model selection based on Baye…
〈Statistical Science / Small Area Estimation〉Institute of Mathematics for Industry, Division of Industrial Mathematical Statistics ResearchStatistical science; small area estimation; mixed-effects mo…
Statistical Science and Small Area Estimation Lab (Masayo Hirose)Institute of Mathematics for Industry, Division of Industrial Mathematical Statistics ResearchStatistical science; small area estimation; mixed-effects mo…
Statistical Analysis and Sparse Estimation LabInstitute of Mathematics for Industry, Division of Industrial Mathematical Statistics ResearchStatistical analysis; sparse estimation; factor analysis; mu…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: “VLT 4LGSF OTA L2 lens measurement on NANOMEFOS (tno kamphues 22)” F. Kamphues/TNO/ESO / CC BY 4.0 (cropped)
- Comparing Which Model Is Valid Using Probabilities: “Coin Toss ( )” ICMA Photos / CC BY-SA 2.0 (cropped)
- The Effect of Observation Noise: “Static viewed on a cathode ray tube television from close up” Boreal11 / CC0 (cropped)
- Dealing with Model Misspecification: “Saturn Rocket Scale Model in the 8- by 6-Foot Supersonic Wind Tunnel (GRC-1960-C-54466)” NASA Glenn Research Center / Public domain (cropped)
- Empirical Research Resolving a Debate in Solid-State Physics: “Electronic density difference Cl Cu111” Cl Cu111 / CC BY-SA 3.0 (cropped)
- Related lab (Bayesian Statistics and Uncertainty Quantification Lab (Satoru Tokuda)): “Taking measurements” Deo photographer / CC BY-SA 4.0 (cropped)
- Related lab (〈Statistical Science / Small Area Estimation〉): “Colorado census statistical areas 2020” Buaidh / CC0 (cropped)
- Related lab (Statistical Science and Small Area Estimation Lab (Masayo Hirose)): “1922 Index of Great Trigonometrical Survey of India” Survey of India, Government of India / Public domain (cropped)
- Related lab (Statistical Analysis and Sparse Estimation Lab): “Factor rotatie” Frederik Beuk / 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.