LGJan 30

DC-LA: Difference-of-Convex Langevin Algorithm

arXiv:2601.22932v1h-index: 11
Originality Incremental advance
AI Analysis

This addresses sampling problems in machine learning and imaging for applications like computed tomography, though it is incremental as it builds on existing Langevin algorithms with a more general framework.

The paper tackles sampling from distributions with non-smooth difference-of-convex regularizers by proposing DC-LA, which converges to the target distribution in Wasserstein distance under distant dissipativity assumptions, and demonstrates accurate uncertainty quantification in computed tomography applications.

We study a sampling problem whose target distribution is $π\propto \exp(-f-r)$ where the data fidelity term $f$ is Lipschitz smooth while the regularizer term $r=r_1-r_2$ is a non-smooth difference-of-convex (DC) function, i.e., $r_1,r_2$ are convex. By leveraging the DC structure of $r$, we can smooth out $r$ by applying Moreau envelopes to $r_1$ and $r_2$ separately. In line of DC programming, we then redistribute the concave part of the regularizer to the data fidelity and study its corresponding proximal Langevin algorithm (termed DC-LA). We establish convergence of DC-LA to the target distribution $π$, up to discretization and smoothing errors, in the $q$-Wasserstein distance for all $q \in \mathbb{N}^*$, under the assumption that $V$ is distant dissipative. Our results improve previous work on non-log-concave sampling in terms of a more general framework and assumptions. Numerical experiments show that DC-LA produces accurate distributions in synthetic settings and reliably provides uncertainty quantification in a real-world Computed Tomography application.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes