mlsanityData to 7 Oct 2026

Convergence Analysis of Schr"odinger-F"ollmer Sampler without Convexity

arXiv 2107.04766 ↗First posted 10 Jul 2021stat.CO cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Schr"odinger-F"ollmer sampler (SFS) is a novel and efficient approach for sampling from possibly unnormalized distributions without ergodicity. SFS is based on the Euler-Maruyama discretization of Schr"odinger-F"ollmer diffusion process d Xt=-nabla Uleft(Xt, tright) d t+d Bt, quad t ∈[0,1],quad X0=0 on the unit interval, which transports the degenerate distribution at time zero to the target distribution at time one. In citesfs21, the consistency of SFS is established under a restricted assumption that %the drift term b(x,t) the potential U(x,t) is uniformly (on t) strongly %concave convex (on x). In this paper we provide a nonasymptotic error bound of SFS in Wasserstein distance under some smooth and bounded conditions on the density ratio of the target distribution over the standard normal distribution, but without requiring the strongly convexity of the potential.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 10 Jul 2021.

Builds on

16 of 41 references.

References · 16

  1. 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 286
  2. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
  3. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
  4. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 195
  5. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 144
  6. 2017User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradientcited by 116
  7. 2019Theoretical guarantees for sampling and inference in generative models with latent diffusionscited by 97
  8. 2017Convergence of Langevin MCMC in KL-divergencecited by 86
  9. 2018Sampling Can Be Faster Than Optimizationcited by 68
  10. 2018Sharp convergence rates for Langevin dynamics in the nonconvex settingcited by 67
  11. 2019Improved Bounds for Discretization of Langevin Diffusions: Near-Optimal Rates without Convexitycited by 38
  12. 2019Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimizationcited by 38
4 more
  1. 2018Coupling and Convergence for Hamiltonian Monte Carlocited by 36
  2. 2015The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Methodcited by 26
  3. 2018On stochastic gradient Langevin dynamics with dependent data streams in the logconcave casecited by 20
  4. 2019On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex casecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 0; 2026: 1.

7 papers.

  1. 2024Probabilistic Forecasting with Stochastic Interpolants and F"ollmer Processescited by 61
  2. 2024Latent Schr"odinger Bridge Diffusion Model for Generative Learningcited by 10
  3. 2024A Practical Diffusion Path for Samplingcited by 5
  4. 2024Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusioncited by 4
  5. 2024An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Controlcited by 1
  6. 2026Variational Optimality of F"ollmer Processes in Generative Diffusionscited by 1
  7. 2024Gradient-Free Score-Based Sampling Methods with Ensemblescited by 0