Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels

Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S. Whitammer, Sergey Samsonov

Keywords: Monte Carlo, MCMC, sampling, Generative Flow Networks, GFlowNets

TL;DR: We propose a novel framework for designing MCMC samplers that can terminate adaptively while maintaining detailed balance, using off-policy entropic RL techniques.

Abstract: Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling. While Markov chain Monte Carlo (MCMC) methods provide asymptotic guarantees, they often suffer from slow mixing and high computational costs due to fixed or manually tuned trajectory lengths. In this work, we propose a novel framework that treats trajectory termination as a learnable component of the sampling dynamics. By framing MCMC within the theory of non-acyclic Generative Flow Networks (GFlowNets), we train state-dependent neural classifiers to decide when a trajectory has reached a high-density region and should terminate. We theoretically establish the connection between optimal classifiers and the target density via detailed balance conditions and introduce a multilevel training scheme to facilitate exploration in complex geometries. Experimental results across various benchmark densities demonstrate that our approach significantly reduces average trajectory lengths while improving mode coverage and mixing compared to standard MCMC baselines.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 134