1. Home
  2. Research
  3. Centers & Labs
  4. RIKEN Center for Advanced Intelligence Project
  5. Generic Technology Research Group

RIKEN Center for Advanced Intelligence Project Information Statistical Mechanics and Dynamics Team

Team Director: Ayaka Sakata (Ph.D.)

Research Summary

Ayaka Sakata

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.

Main Research Fields

  • Informatics

Related Research Fields

  • Interdisciplinary Science & Engineering
  • Mathematical & Physical Sciences
  • Soft computing
  • Intelligent informatics
  • Mathematical physics & Fundamental condensed matter physics

Keywords

  • Statistical Physics for Information Processing
  • Approximate Inference
  • Statistical Modeling
  • Statistical Sampling

Selected Publications

Papers with an asterisk(*) are based on research conducted outside of RIKEN.

  • 1. *Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi
    "Effect of Weight Quantization on Learning Models by Typical Case Analysis"
    IEEE International Symposium on Information Processing, 357-362 (2024)
  • 2. *Ayaka Sakata and Kunihiko Kaneko
    "Evolutionary Shaping of Low-Dimensional Path Facilitates Robust and Plastic Switching Between Phenotypes"
    Physical Review Research 5(4) 043296 (2023).
  • 3. *Ayaka Sakata and Yoshiyuki Kabashima
    "Decision Theoretic Cutoff and ROC Analysis for Bayesian Optimal Group Testing"
    IEEE Transactions on Information Theory, 69(9), 5902-5920 (2023).
  • 4. *Ayaka Sakata
    "Prediction Errors for Penalized Regressions based on Generalized Approximate Message Passing"
    J. Phys. A: Math. Theor. 56 043001 (2023).
  • 5. *Ayaka Sakata and Tomoyuki Obuchi
    "Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control"
    Journal of Statistical Mechanics: Theory and Experiment, vol. 2021(9), 093401 (2021).
  • 6. *Ayaka Sakata
    "Active pooling design in group testing based on Bayesian posterior prediction"
    Phys. Rev. E 103, 022110 (2021).
  • 7. *Ayaka Sakata
    "Bayesian inference of infected patients in group testing with prevalence estimation"
    J. Phys. Soc. Jpn. 89, 084001 (2020). Editors' choice
  • 8. *Ayaka Sakata and Kunihiko Kaneko
    "Dimensional reduction in evolving spin-glass model: correlation of phenotypic responses to environmental and mutational changes"
    Physical Review Letters Vol. 124, No. 21, 218101 (2020).
  • 9. *Tomoyuki Obuchi and Ayaka Sakata
    "Cross validation in sparse linear regression with piecewise continuous nonconvex penalties and its acceleration"
    Journal of Physics A: Mathematical and Theoretical, vol. 52, 414003 (2019).
  • 10. *Ayaka Sakata
    "Estimator of Prediction Error Based on Approximate Message Passing for Penalized Linear Regression"
    Journal of Statistical Mechanics: Theory and Experiment, vol. 2018, pp. 063404-1-24 (2018).

Lab Members

Principal investigator

Ayaka Sakata
Team Director

Contact Information

Email: ayaka.sakata@riken.jp

Top