AI RESEARCH
Dale meets Langevin: A Multiplicative Denoising Diffusion Model
arXiv CS.LG
•
ArXi:2510.02730v2 Announce Type: replace Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience. Since the marginal distribution of geometric Brownian motion (GBM) at any fixed time is log-normal, this convergence property reveals a natural connection between EGD and GBM-based stochastic processes.