Speaker：Zhijian He（South China University of Technology）

Time：2022-11-04, 15:00

Location：Tencent Meeting ID：403-283-780（No Password）

Abstract:

Variational inference (VI) is usually computationally effective compared to simulation-based methods, such as Markov chain Monte Carlo. In many applications typically arising from natural and social sciences, the likelihoods concerning probabilistic models are intractable, but can be unbiasedly estimated. In this talk, I will show how to use VI to approximate Bayesian posterior by a tractable distribution chosen to minimize the Kullback-Leibler (KL) divergence between the posterior distribution and the variational distribution in the likelihood-free setting. To this end, our recent work proposed unbiased estimators based on multilevel Monte Carlo (MLMC) for the gradient of KL divergence so that the minimizer of the KL divergence is obtained by the stochastic gradient decent algorithm. This is joint work with Xiaoqun Wang, Zhenghang Xu.