Sampling from high-dimensional distributions poses significant computational challenges. We introduce Subspace Langevin Monte Carlo (SLMC), a novel and efficient sampling method that generalizes coordinate and preconditioned Langevin Monte Carlo. At a higher level, our method can be viewed as a natural extension of subspace descent techniques from Euclidean space to Wasserstein space. If time permits, we will discuss subspace Wasserstein descent in other settings.
Back to Long Programs
Copyright. All Rights Reserved.