Reflected anchored Langevin dynamics (RALD), a reflected diffusion that converges to non-differentiable targets on constrained domains on constrained domains is introduced.
Abstract
First order Langevin algorithms for constrained sampling in machine learning, such as projected Langevin Monte Carlo which are based on discretizations of reflected Langevin dynamics, require differentiable log densities that limits their applicability. This paper introduces reflected anchored Langevin dynamics (RALD), a reflected diffusion that converges to non-differentiable targets on constrained domains. The method uses a smooth anchored reference potential and multiplies the drift and noise covariance of its reflected Langevin dynamics by the same state dependent scaling factor. Its Euler-Maruyama discretization with projection gives reflected anchored Langevin Monte Carlo (RALMC) algorithm. We prove explicit convergence bounds and iteration complexity for RALMC in the 2-Wasserstein distance to the target distribution. Numerical experiments are provided to illustrate the theoretical predictions and the empirical performance of the method.
Classical Langevin Monte Carlo algorithms, such as the unadjusted Langevin algorithm (ULA), are based on discretization schemes of the overdamped Langevin dynamics and are widely used for sampling in machine learning because they scale to high dimensions and large datasets. However, they require differentiable log-dens...
Qi Feng, Hoang M. Nguyen, Ling-Jiong Zhu· 0 citations
Stochastic-gradient Langevin methods are sampling algorithms that replace the gradient of the log probability density by a noisy, possibly biased evaluation. We study how such gradient-evaluation errors affect the Euler and randomized midpoint discretizations of Langevin dynamics by comparing each noisy chain with its...
A stochastic first-order version of the Mirror Langevin Algorithm (sFO-MLA) is studied and finite-time Wasserstein guarantees for sFO-MLA are established that explicitly separate mixing, Euler--Maruyama discretization, and stochastic-gradient errors.
Rui-Ting Tong, Antik Chakraborty, Raghu Pasupathy· 0 citations
The saturated unadjusted Langevin algorithm (SULA) is proposed, a saturated gradient drift with a gradient-informed state-dependent diffusion, while preserving first-order consistency with the Langevin diffusion, and SG-SULA, a stochastic-gradient version of SULA that rescales the stochastic gradient using a Gaussian C...
Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales. However, target trajectories, used to identify and interpret such dynamics, are often inaccessible: only biased or static...
V. Kostić, Karim Lounici, H. Halconruy et al.· 0 citations
We develop an exact simulation algorithm for scalar diffusion paths and diffusion bridges when the Poisson potential is unbounded in both tails. The method reconstructs the realized range of a Brownian bridge proposal by sampling its maximum and location, together with the maxima and locations of the two adjacent restr...
Radu Herbei, Kumar Somnath· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 6, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.