Convergence Analysis of Schr{ö}dinger-F{ö}llmer Sampler without Convexity
arXiv:2107.04766
Abstract
Schrödinger-Föllmer 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 Schrödinger-Föllmer diffusion process on the unit interval, which transports the degenerate distribution at time zero to the target distribution at time one. In \cite{sfs21}, the consistency of SFS is established under a restricted assumption that %the drift term the potential is uniformly (on ) strongly %concave convex (on ). 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.
arXiv commentarXiv admin note: text overlap with arXiv:2106.10880
References in corpus (9)
- MCMC using Hamiltonian dynamics
- Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
- Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
- Convergence of Langevin MCMC in KL-divergence
- Poincaré and logarithmic Sobolev inequalities by decomposition of the energy landscape
- On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case
- Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization
- Log-Sobolev inequalities: Different roles of Ric and Hess
- On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case