Dale meets Langevin: A Multiplicative Denoising Diffusion Model 事件

Dale meets Langevin: A Multiplicative Denoising Diffusion Model arXiv:2510.02730v2 Announce Type: replace-cross Abstract: 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 n