Penalized overdamped and underdamped Langevin Monte Carlo algorithms for constrained sampling

Mert Gürbüzbalaban; Yuanhan Hu; Lingjiong Zhu

Publications · Journal article · J. Mach. Learn. Res. 2024

Penalized overdamped and underdamped Langevin Monte Carlo algorithms for constrained sampling

Mert Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu

Journal of Machine Learning Research, 25(263), pp. 1–67, 2024.

Publisher page Code

In brief

Develops penalty-based overdamped and underdamped Langevin Monte Carlo methods for sampling from distributions supported on constraint sets, with non-asymptotic performance guarantees.

Topics

Sampling & Langevin algorithms

Cite

@article{gurbuzbalaban2024constrained,
  title   = {Penalized overdamped and underdamped Langevin Monte Carlo algorithms for constrained sampling},
  author  = {Mert Gürbüzbalaban and Yuanhan Hu and Lingjiong Zhu},
  year    = {2024},
  journal = {Journal of Machine Learning Research},
  volume  = {25(263)},
  pages   = {1--67},
  url     = {https://jmlr.org/papers/v25/22-1443.html},
}

Relatedsame topics

Anchored Langevin algorithms (arXiv, 2025)
DIGing-SGLD: decentralized and scalable Langevin sampling over time-varying networks (arXiv, 2025)
High-order Langevin Monte Carlo algorithms (arXiv, 2025)
Generalized EXTRA stochastic gradient Langevin dynamics (arXiv, 2024)
Uniform-in-time Wasserstein stability bounds for (noisy) stochastic gradient descent (NeurIPS, 2023)

← All publications · Research program · Mert Gürbüzbalaban