When Langevin Monte Carlo Meets Randomization: Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness

arXiv:2509.25630v2 Announce Type: replace-cross Abstract: Efficient sampling from complex and high dimensional target distributions turns out to be a fundamental task in diverse disciplines such as scientific computing, statistics and machine learning. In this paper, we revisit the randomized Langevin Monte Carlo (RLMC) for sampling from high dimensional distributions without log-concavity. Under the gradient Lipschitz condition and the log-Sobolev inequality, we prove a uniform-in-time error bound in W_2-distance of order O(sqrt{d}h) for the RLMC sampling algorithm, which matches the best one in the literature under the log-concavity condition. Moreover, when the gradient of the potential U is non-globally Lipschitz with superlinear growth, modified RLMC algorithms are proposed and analyzed, with non-asymptotic error bounds established. To the best of our knowledge, the modified RLMC algorithms and their non-asymptotic error bounds are new in the non-globally Lipschitz setting.

Related

• Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
• High Probability Guarantees for Random Reshuffling
• Scaling flow-based approaches for topology sampling in SU(3) gauge theory
• Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization
• A fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation

Source: arXiv cs.LG | 2026-04-22