Probably approximate Bayesian computation: nonasymptotic convergence of ABC under misspecification
Approximate Bayesian computation (ABC) is a widely used inference method in Bayesian statistics to bypass the point-wise computation of the likelihood. In this paper we develop theoretical bounds for the distance between the statistics used in ABC. We show that some versions of ABC are inherently robust to misspecification. The bounds are given in the form of oracle inequalities for a finite sample size. The dependence on the dimension of the parameter space and the number of statistics is made explicit. The results are shown to be amenable to oracle inequalities in parameter space. We apply our theoretical results to given prior distributions and data generating processes, including a non-parametric regression model. In a second part of the paper, we propose a sequential Monte Carlo (SMC) to sample from the pseudo-posterior, improving upon the state of the art samplers.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Practical bounds on the error of Bayesian posterior approximations: A nonasymptotic approach
Bayesian inference typically requires the computation of an approximation to the posterior distribution. An important requirement for an approximate Bayesian inference algorithm is to output high-accuracy posterior mean …
Bayesian InferenceVariational InferenceNonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
We provide a nonasymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) to a target measure in Wasserstein-2 distance without assuming log-concavity. Our analysis quantifies key …
Bayesian InferenceGeneralization BoundsStochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of on…
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This mo…
The Probably Approximately Correct Learning Model in Computational Learning Theory
This survey paper gives an overview of various known results on learning classes of Boolean functions in Valiant's Probably Approximately Correct (PAC) learning model and its commonly studied variants.