Members
-
Team directorAyaka Sakata
Introduction
Based on the methodology of statistical physics, our team seeks to develop a fundamental understanding of various processes in modern machine learning, including learning, inference, and generation. In particular, we are working to establish novel theories and algorithms that enhance the efficiency of approximate inference and sampling, grounded in both equilibrium statistical mechanics and dynamical perspectives. These efforts are expected to deepen and extend the mathematical foundations that underpin machine learning. Furthermore, by organizing and integrating knowledge in the interdisciplinary domain between physics and machine learning, we aim to promote cross-disciplinary collaboration and contribute to a more universal understanding of learning systems.
Approximate Inference
Statistical Modeling
Statistical Sampling
