AI RESEARCH

Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?

arXiv CS.LG

ArXi:2602.06500v2 Announce Type: replace Scaling inference methods such as Marko chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promising recent proposal, microcanonical Langevin Monte Carlo, has shown state-of-the-art performance across a wide range of problems. However, its reliance on full-dataset gradients makes it prohibitively expensive for large-scale problems.