Large Spin-Wave Fluctuations Suppress Activity in Malthusian Flocks
arXiv:2608.05805
2026
Dynamics
1 ideas extracted · analyzed Aug 31, 2026
What the math gives to ML
The paper derives a concrete noise-induced renormalization mechanism: Gaussian spin-wave fluctuations dress a nonlinear activity coupling by an exponential Debye-Waller factor, causing the effective nonlinearity to collapse when fluctuation variance is large. This is transferable as a variance-aware gate on nonlinear residual branches or interaction terms, rather than treating activation variance only through normalization. The most direct experiment is to multiply a learned nonlinear update by an online estimate of exp(-v/2), testing whether high-noise or unstable training automatically becomes closer to a stable linearized model while retaining full nonlinearity in low-variance regimes.
Ideas from this paper
Unverified
2026
Use the paper's exponential dressing of an activity coupling as an adaptive gate on a neural network's nonlinear residual branch. The branch is strongly suppressed when the local activation fluctuation variance is high, producing an automatically linearized and more stable update, while low-variance representations preserve the learned nonlinear interaction.
Useful5/10
Difficulty3/10
Novelty6/10