Machine Learning / Deep Learning
Understand patterns from large-scale data.
In the field of machine learning and deep learning, technology that contributes to practical use has been born due to the recent development of computer technology and communication technology. 
Now, machine learning technology is expected to solve many important issues in the real world. 
The issues that we need to solve are extremely complex and diverse, including abnormality detection, automatic operation, plant and robot control, and drug discovery. 
To solve these issues, PFN gathers experts from a wide range of fields around machine learning, from basic theory to actual application, and works together to conduct research. 
The results obtained there will be returned in the form of paper presentations, open source library publications, and application to real systems, and will respond widely to the demands of society.
Publications
Flow matching achieves almost minimax optimal convergence
ICLR2025
By : Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama
Deep Bayesian Filter for Bayes-Faithful Data Assimilation
ICML2025
By : Yuta Tarumi, Keisuke Fukuda, Shin-ichi Maeda
Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
ICML 2023
By : Yuri Kinoshita, Kenta Oono, Kenji Fukumizu, Yuichi Yoshida, Shin-ichi Maeda




