Yoshinobu Kawahara

Spectral analysis reveals that increasing latent dimensions in Koopman autoencoders improves dynamics learning by concentrating learned eigenvalues in low-residual regions, not just by reducing one-step prediction error.

Unlocking causal discovery in time-series by disentangling instantaneous and lagged influences, even with nonstationary dynamics.

Noise doesn't have to derail your search for fractional differential equations—Weak-Pareto recovers accurate structures even under significant measurement noise.