Sampling from probability distributions is a crucial task in both statistics and machine learning. However, when the target distribution does not permit exact sampling, researchers often rely on Markov chain Monte Carlo (MCMC) methods.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

We introduce shielded Langevin Monte Carlo (LMC), a constrained sampler inspired by navigation functions, capable of sampling from unnormalized target distributions defined over punctured supports. In other words, this approach samples from non-convex spaces defined as convex sets with convex holes. This defines a novel and challenging problem in constrained sampling. To do so, the sampler incorporates a combination of a spatially adaptive temperature and a repulsive drift to ensure that samples remain within the feasible region. Experiments on a 2D Gaussian mixture and multiple-input multiple-output (MIMO) symbol detection showcase the advantages of the proposed shielded LMC in contrast to unconstrained cases.

Furthermore, many important constrained distributions are inherently non-log-concave.

A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality).

Sampling from log-concave distributions is a central problem in statistics and machine learning. Prior work establishes theoretical guarantees for Langevin Monte Carlo algorithm based on overdamped and underdamped Langevin dynamics and, more recently, some third-order variants. In this paper, we introduce a new sampling algorithm built on a general $K$th-order Langevin dynamics, extending beyond second- and third-order methods. To discretize the $K$th-order dynamics, we approximate the drift induced by the potential via Lagrange interpolation and refine the node values at the interpolation points using Picard-iteration corrections, yielding a flexible scheme that fully utilizes the acceleration of higher-order Langevin dynamics. For targets with smooth, strongly log-concave densities, we prove dimension-dependent convergence in Wasserstein distance: the sampler achieves $\varepsilon$-accuracy within $\widetilde O(d^{\frac{K-1}{2K-3}}\varepsilon^{-\frac{2}{2K-3}})$ gradient evaluations for $K \ge 3$. To our best knowledge, this is the first sampling algorithm achieving such query complexity. The rate improves with the order $K$ increases, yielding better rates than existing first to third-order approaches.