2 papers
cs.LG2026
Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario
Alex Alì Maleknia, Yuzuru Sato
Vanishing gradients and overfitting are central problems in machine learning, yet are typically analyzed in asymptotic regimes that obscure their dynamical origins. Here we provide…
nlin.CD2025
Time-delayed feedback control for random dynamical systems
Miki U. Kobayashi, Yuzuru Sato
We extend the Pyragas time-delayed feedback control (TDFC) to apply it to random dynamical systems and introduce an extended classification based on Lyapunov exponents and trajecto…