all AI news
Stochastic Langevin Differential Inclusions with Applications to Machine Learning. (arXiv:2206.11533v1 [math.OC])
Web: http://arxiv.org/abs/2206.11533
cs.LG updates on arXiv.org arxiv.org
Stochastic differential equations of Langevin-diffusion form have received
significant recent, thanks to their foundational role in both Bayesian sampling
algorithms and optimization in machine learning. In the latter, they serve as a
conceptual model of the stochastic gradient flow in training over-parametrized
models. However, the literature typically assumes smoothness of the potential,
whose gradient is the drift term. Nevertheless, there are many problems, for
which the potential function is not continuously differentiable, and hence the
drift is not Lipschitz-continuous everywhere. …
applications arxiv learning machine machine learning math stochastic