Masahiro Fujisawa (藤澤 将広), Ph.D.

Research Interests

  • (Bayesian) Machine Learning
  • (Generalized) Bayesian inference
  • Likelihood-free (or simulator-based) inference
  • Robustness and generalization

CV

My CV is here.

News

  • June 18, 2025: Our new paper, Flight trajectory modeling reveals species-specific obstacle avoidance policies in echolocating bats, was made publicly available on bioRxiv, coauthored by Dr. Yu Teshima (Japan Agency for Marine-Earth Science and Technology), Shoko Genda (Doshisha University), Yota Aoki (Doshisha University), Prof. Shizuko Hiryu (Doshisha University), and Prof. Keisuke Fujii (Nagoya University / RIKEN AIP).

  • May 26, 2025: Our new paper, Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables, was made publicly available on arXiv, coauthored by Prof. Futoshi Futami (The University of Osaka / RIKEN AIP).

  • May 23, 2025: Our new paper, Scalable Valuation of Human Feedback through Provably Robust Model Alignment, was made publicly available on arXiv, coauthored by Masaki Adachi (University of Oxford / Toyota Motor Corporation) and Prof. Michael A. Osborn (University of Oxford).

  • May 16, 2025: Our paper, “Fixing the Pitfalls of Probabilistic Time-Series Forecasting Evaluation by Kernel Quadrature,” has been accepted to ProbNum25! Many thanks to the coauthors, the reviewers for their valuable feedback, and to the ACs, SACs, and PCs for their hard work amidst their busy schedules.

  • May 1, 2025: Our paper, “PAC-Bayes Analysis for Recalibration in Classification,” has been accepted to ICML 2025! Many thanks to the reviewers for their valuable feedback, and to the ACs, SACs, and PCs for their hard work amidst their busy schedules.

  • March 14, 2025: I was honored to receive the RIKEN BAIHO Award (Research Incentive Award at RIKEN) alongside Prof. Futoshi Futami. I would like to express my sincere gratitude to Prof. Sugiyama, Prof. Futami, and everyone who evaluated our work.