Properties and limitations of geometric tempering for gradient flow dynamics

arXiv:2604.20301v1 Announce Type: cross Abstract: We consider the problem of sampling from a probability distribution pi. It is well known that this can be written as an optimisation problem over the space of probability distributions in which we aim to minimise the Kullback--Leibler divergence from pi. We consider the effect of replacing pi with a sequence of moving targets (pi_t)_{tge0} defined via geometric tempering on the Wasserstein and Fisher--Rao gradient flows. We show that convergence occurs exponentially in continuous time, providing novel bounds in both cases. We also consider popular time discretisations and explore their convergence properties. We show that in the Fisher--Rao case, replacing the target distribution with a geometric mixture of initial and target distribution never leads to a convergence speed up both in continuous time and in discrete time. Finally, we explore the gradient flow structure of tempered dynamics and derive novel adaptive tempering schedules.

Related

• Generative Path-Finding Method for Wasserstein Gradient Flow
• When Langevin Monte Carlo Meets Randomization: Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness
• Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
• Computational bottlenecks for denoising diffusions

Source: arXiv cs.LG | 2026-04-23