4 papers
A Trust Region Approach for Learning Schrödinger Bridges
Takeshi Koshizuka, Denis Blessing, Max Zimmer +2
We study the numerical approximation of Schrödinger Bridges in the setting where samples from the target distribution are unavailable and only an unnormalized target density is giv…
Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms
Takeshi Koshizuka, Takaharu Yaguchi
Disruption predictors must warn the plasma control system early enough for the intended response, and the required warning time differs between mitigation and avoidance. We view a…
Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
Takeshi Koshizuka, Issei Sato
Physics-informed machine learning is gaining significant traction for enhancing statistical performance and sample efficiency through the integration of physical knowledge. However…
Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka +1
In this paper, we explores the expressivity and trainability of the Fourier Neural Operator (FNO). We establish a mean-field theory for the FNO, analyzing the behavior of the rando…