الباحثون

Yingli Wang

المنشورات 2

نسخة أولية وصول مفتوح

Accelerating Non-Smooth and Heavy-Tailed Sampling

Pervez Ali, Xiaoyu Wang, Yingli Wang وآخرون · 2026

Anchored Langevin dynamics (ALD) is useful for non-smooth sampling where the density of the target distribution is possibly non-differentiable and heavy-tailed; reflected anchored Langevin dynamics (RALD) can sample possibly non-differentiable target density on a constrained domain. In this paper, we propose and study …

نسخة أولية وصول مفتوح

Reflected Anchored Langevin Algorithms

Changwei Tu, Xiaoyu Wang, Yingli Wang وآخرون · 2026

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), …

المؤلفون المشاركون