AI RESEARCH
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
arXiv CS.LG
•
ArXi:2605.22644v1 Announce Type: new Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate. In this work, we propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling.