Backend
Kinetic Langevin Splitting Schemes for Constrained Sampling
arXiv stat.ML0 views
arXiv:2603.23397v3 Announce Type: replace-cross Abstract: Constrained sampling, the task of generating samples from a distribution restricted to a convex set, is an important problem in computational statistics. In this paper, we propose new unadjusted sampling algorithms obtained by applying the symmetric BAOAB and ABOBA splittings, of the kinetic Langevin dynamics, to a penalized surrogate of the constrained target. This also includes their stochastic gradient versions. Since the Hessian of the penalized surrogate is discontinuous across the boundary of the constraint set, analyses relying on a Lipschitz Hessian do not apply. We therefore develop an analysis based only on strong convexity and smoothness, proving one-step Wasserstein contraction schemes, non-asymptotic Wasserstein bounds of both schemes and complexity bounds. The resulting complexities for the stochastic gradient versions improve substantially on traditional Euler-type discretizations. Numerical experiments verify our theory, which is tested on a toy problem and Bayesian constrained regression problem. Overall, the splitting schemes demonstrate stability at step sizes several times larger than Euler-type methods, require five to seventeen times fewer gradient evaluations for a given accuracy.
Source:https://arxiv.org/abs/2603.23397PreviousSignature-Kernel Based Evaluation Metrics for Robust Probabilistic and Tail-Event ForecastingNextOptimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
Related posts
User Acceptance Testing for Founders: Six Steps Before You Sign Off
0dev.to Testing
IP44 Socket vs IP67: Which Rating Fits Your Site?
0dev.to Testing
How to Create an Effective API Test Plan: A Practical Guide for QA Engineers and Developers
0dev.to Testing
Penetration Testing on Patch Day: A 24-Hour Retest Sequence You Can Copy
0dev.to Testing
![Vision Language Action Models — Ch.07: Embodied AI [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F0mybcu28jlrfrhckufnu.png)
Vision Language Action Models — Ch.07: Embodied AI [EN]
0dev.to Programming
![Vision Language Action Models — Ch.03: Language Models for Robotics [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fd5l4ehmkuixtsjqybw18.png)
Vision Language Action Models — Ch.03: Language Models for Robotics [EN]
0dev.to Programming