We show that the behavior of stochastic gradient descent is related to Bayesian statistics by showing that SGD is effectively diffusion on a fractal landscape, where the fractal dimension can be accounted for in a purely Bayesian way. By doing this we show that SGD can be regarded as a modified Bayesian sampler which accounts for accessibility constraints induced by the fractal structure of the loss landscape. We verify our results experimentally by examining the diffusion of weights during training. These results offer insight into the factors which determine the learning process, and seemingly answer the question of how SGD and purely Bayesian sampling are related.
View on arXiv@article{hennick2025_2503.22478,
title={ Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent },
author={ Max Hennick and Stijn De Baerdemacker },
journal={arXiv preprint arXiv:2503.22478},
year={ 2025 }
}