Search Results for author: Masahiro Fujisawa

Found 3 papers, 0 papers with code

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

no code implementations10 Oct 2023 Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka, Issei Sato

Building upon this observation, we also propose an edge of chaos initialization scheme for FNO to mitigate the negative initialization bias leading to training instability.

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

no code implementations13 Jun 2020 Masahiro Fujisawa, Takeshi Teshima, Issei Sato, Masashi Sugiyama

Approximate Bayesian computation (ABC) is a likelihood-free inference method that has been employed in various applications.

Multilevel Monte Carlo Variational Inference

no code implementations1 Feb 2019 Masahiro Fujisawa, Issei Sato

We theoretically show that, with our method, the variance of the gradient estimator decreases as optimization proceeds and that a learning rate scheduler function helps improve the convergence.

Stochastic Optimization Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.