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

The Transaction Only Covers Your Database. The Provider Key Is What Saves You
0dev.to Database

Go 1.28 will flag the error your rows.Next() loop forgets
0dev.to Database
How zkDatabase Works: From Data Sampling to Verifiable Query Results
0dev.to Database
LogTreeDB: Building a Crash-Safe, Zero-Dependency Document Database from Scratch in C++17
0dev.to Database
CratesBump: A Version-Bump Dataset for the Rust Ecosystem
0arXiv cs.SE
Integrating AI Coding Agents Into Scientific Research
0arXiv cs.SE