2 papers
cond-mat.dis-nn2026
Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Generalization Beyond Overfitting in Machine Learning
Chan Li, Nigel Goldenfeld
The remarkable ability of modern neural networks to generalize improves with increasing network capacity, even when the number of model parameters or effective degrees of freedom e…
cond-mat.stat-mech2025
Self-consistent expansion and field-theoretic renormalization group for a singular nonlinear diffusion equation with anomalous scaling
Minhui Zhu, Nigel Goldenfeld
The method of self-consistent expansions is a powerful tool for handling strong coupling problems that might otherwise be beyond the reach of perturbation theory, providing surpris…