paper-with-me

홈 › Papers

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

2026-06-15 · Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S. Whitammer, Sergey Samsonov arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.16073

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

Similar Papers 제목 키워드 기반

Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

2021-03-29 · Zhedong Zheng, Yi Yang

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled t…

Domain AdaptationScene SegmentationSemantic SegmentationSemi-Supervised Image Classification+2

Sequential Design for Optimal Stopping Problems

2013-09-16 · Robert B. Gramacy, Mike Ludkovski

We propose a new approach to solve optimal stopping problems via simulation. Working within the backward dynamic programming/Snell envelope framework, we augment the methodology of Longstaff-Schwartz that focuses on appr…

Active Learning

Early Stopping in Contextual Bandits and Inferences

2025-02-05 · Zihan Cui

Bandit algorithms sequentially accumulate data using adaptive sampling policies, offering flexibility for real-world applications. However, excessive sampling can be costly, motivating the devolopment of early stopping m…

Decision MakingMulti-Armed Bandits

Continuous-time Optimal Stopping through Deep Reinforcement Learning

2026-06-16 · Cosmin Borsa, Michael Ludkovski arxiv

Simulation based solvers for optimal stopping problems must discretize the stopping decision. Under classical dynamic programming, a coarse exercise grid with only a few stopping opportunities can materially undervalue t…

Computational EfficiencyReinforcement Learning

How much Data do We Need? Sequential Data Collection for Stochastic Programming

2026-07-11 · Xin Li, Juergen Branke, Xuan Vinh Doan arxiv

Data-driven optimization often requires collecting data to estimate uncertain model parameters before solving the underlying decision problem. In practice, however, data acquisition may incur non-negligible costs, making…

Stochastic Optimization