activity
20242026
collaborators

5 papers

stat.AP2026

Data-driven sparse identification of governing PDEs via knockoff filters and multi-criteria trade-offs

Pongpisit Thanasutives, Naichang Ke, Yoshinobu Kawahara

We propose KO-PDE-IDENT, a data-driven framework for identifying parsimonious partial differential equations (PDEs) with false discovery rate (FDR) control. PDE discovery from nois…

math.DS2025

Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces

Isao Ishikawa, Yuka Hashimoto, Masahiro Ikeda +1

This paper presents a novel approach for estimating the Koopman operator defined on a reproducing kernel Hilbert space (RKHS) and its spectra. We propose an estimation method, what…

math.DS2025

Generalized Stochastic Resilience for Early Warning Signals Based on Koopman Operator

Yuta Miyauchi, Masahiro Ikeda, Yoshinobu Kawahara

Developing methods for detecting tipping phenomena at an early stage is an important problem in various fields such as ecology, medicine, and economics. A tipping phenomenon is cha…

nlin.AO2025

Operator-theoretic Analysis of Mutual Interactions in Synchronized Dynamics

Yuka Hashimoto, Masahiro Ikeda, Hiroya Nakao +1

Analyzing synchronized nonlinear oscillators is one of the most important and attractive topics in nonlinear science. By understanding the interactions between the oscillators, we…

cs.LG2024

Koopman Spectrum Nonlinear Regulators and Efficient Online Learning

Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey +3

Most modern reinforcement learning algorithms optimize a cumulative single-step cost along a trajectory. The optimized motions are often 'unnatural', representing, for example, beh…