High Dimensional Non-Gaussian Bayesian Inference with Transport Maps

来源 :第八届工业与应用数学国际大会 | 被引量 : 0次 | 上传用户：hbimac

【摘要】

：

　　Characterizing high dimensional posterior distributions in the context of nonlinear and non-Gaussian Bayesian inverse problems is a wellknown challenging ta

【作者】

：

Spantini Alessio Marzouk Youssef

【机构】

：

MIT

【出处】

：

第八届工业与应用数学国际大会

【发表日期】

：

2015年期

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　Characterizing high dimensional posterior distributions in the context of nonlinear and non-Gaussian Bayesian inverse problems is a wellknown challenging task.

其他文献

Rehabilitation Robot:A Personal Perspective of Control Theory & Practice

　　This talk will mainly address the system design of a reclining type rehabilitation robot for lower limbs,and also discuss the control strategies and related

会议

Communication-based Fault Detection and Isolation for Multi-agent Systems

　　We propose a communication-based fault detection and isolation framework for multi-agent systems.All the fault processing operation is achieved by controlli

会议

Predictive Control Synthesis for Networked Control Systems

　　Networked control systems(NCSs)are a class of complex dynamical systems in which the distributed system components are connected over communication networks

会议

Complex System Control and Applications Ⅱ

　　It's arguable that complex systems have been studied for many years,but only after the discovery of chaos in deterministic systems did people realize that t

会议

Decentralized Tracking Algorithms for Three Manipulators Subject to Motion Constraints

　　We consider a tracking problem for three manipulators grasping a rigid object.The control objective is to coordinate the movements of the manipulators using

会议

Operator-weighted MCMC on Function Spaces

　　Many inference problems require exploring the posterior distribution of high-dimensional parameters,which in principle can be described as functions.

会议

Networked Systems and Optimization

　　There is a class of complex large-scale systems which are composedcomposed of many physically or geographically divided subsystems.Each subsystem interacts

会议

Flexible Distributed Model Predictive Control Coordination Strategies - Several Viewpoints

　　Some Distributed Model Predictive Control(DMPC)coordination strategies for improving the performance of entire closed-loop system are reviewed.

会议

Advances in Generalised Metropolis-Hastings Algorithms

　　A recent generalization of the Metropolis−Hastings algorithm allows for parallelizing a single chain using existing MCMC methods(Calderhead,PNAS,2014).

会议

Multilevel Sequential Monte Carlo Samplers

　　The approximation of the posterior distribution associated to a Bayesian inverse problem is decomposed into a hierarchy consisting of a telescoping sum of i

会议

High Dimensional Non-Gaussian Bayesian Inference with Transport Maps

与本文相关的学术论文