Masahiro Fujisawa

According to our database, Masahiro Fujisawa authored at least 14 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables.

Futoshi Futami, Masahiro Fujisawa

CoRR, May, 2025

Scalable Valuation of Human Feedback through Provably Robust Model Alignment.

Masahiro Fujisawa, Masaki Adachi, Michael A. Osborne

CoRR, May, 2025

Variational OOD State Correction for Offline Reinforcement Learning.

Ke Jiang, Wen Jiang, Masahiro Fujisawa, Xiaoyang Tan

CoRR, May, 2025

Fixing the Pitfalls of Probabilistic Time-Series Forecasting Evaluation by Kernel Quadrature.

Masaki Adachi, Masahiro Fujisawa, Michael A. Osborne

CoRR, March, 2025

On the Convergence of SVGD in KL divergence via Approximate gradient flow.

Masahiro Fujisawa, Futoshi Futami

Trans. Mach. Learn. Res., 2025

2024

PAC-Bayes Analysis for Recalibration in Classification.

Masahiro Fujisawa, Futoshi Futami

CoRR, 2024

Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective.

Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Information-theoretic Generalization Analysis for Expected Calibration Error.

Futoshi Futami, Masahiro Fujisawa

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Initialization Bias of Fourier Neural Operator: Revisiting the Edge of Chaos.

Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato

CoRR, 2023

Time-Independent Information-Theoretic Generalization Bounds for SGLD.

Futoshi Futami, Masahiro Fujisawa

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2021

Multilevel Monte Carlo Variational Inference.

Masahiro Fujisawa, Issei Sato

J. Mach. Learn. Res., 2021

γ-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator.

Masahiro Fujisawa, Takeshi Teshima, Issei Sato, Masashi Sugiyama

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

γ-ABC: Outlier-Robust Approximate Bayesian Computation based on Robust Divergence Estimator.

Masahiro Fujisawa, Takeshi Teshima, Issei Sato

CoRR, 2020

2019

Multi-level Monte Carlo Variational Inference.

Masahiro Fujisawa, Issei Sato

CoRR, 2019