Special Session 19: Topics on singular stochastic equations

Schrodinger-Follmer Sampler
Yanyan Liu
Wuhan University
Peoples Rep of China
Co-Author(s):    Jian Huang , Yuling Jiao, Lican Kang , Xu Liao, Jin Liu,Yanyan Liu
Abstract:
Sampling from probability distributions is an important problem in statistics and machine learning, specially in Bayesian inference when integration with respect to posterior distribution is intractable and sampling from the posterior is the only viable option for inference. In this paper, we propose Schrodinger-Follmer sampler (SFS), a novel approach to sampling from possibly unnormalized distributions. The proposed SFS is based on the Schrodinger-Follmer diffusion process on the unit interval with a time-dependent drift term, which transports the degenerate distribution at time zero to the target distribution at time one. Compared with the existing Markov chain Monte Carlo samplers that require ergodicity, SFS does not need to have the property of ergodicity. Computationally, SFS can be easily implemented using the Euler-Maruyama discretization. In theoretical analysis, we establish nonasymptotic error bounds for the sampling distribution of SFS in the Wasserstein distance under reasonable conditions. We conduct numerical experiments to evaluate the performance of SFS and demonstrate that it is able to generate samples with better quality than several existing methods.