University College London(伦敦大学学院);Aalto University(阿尔托大学);Getulio Vargas Foundation(热图利奥·瓦加斯基金会);University of Manchester(曼彻斯特大学);University of Helsinki(赫尔辛基大学)
Daniel Augusto de Souza, Diego Mesquita, Samuel Kaski, Luigi Acerbi
Embarrassingly parallel Markov Chain Monte Carlo (MCMC) exploits parallel computing to scale Bayesian inference to large datasets by using a two-step approach. First, MCMC is run in parallel on (sub)posteriors defined on data partitions. Then, a server combines local results. While efficient, this framework is very sensitive to the quality of subposterior sampling. Common sampling problems such as missing modes or misrepresentation of low-density regions are amplified -- instead of being corrected -- in the combination phase, leading to catastrophic failures. In this work, we propose a novel combination strategy to mitigate this issue. Our strategy, Parallel Active Inference (PAI), leverages Gaussian Process (GP) surrogate modeling and active learning. After fitting GPs to subposteriors, PAI (i) shares information between GP surrogates to cover missing modes; and (ii) uses active sampling to individually refine subposterior approximations. We validate PAI in challenging benchmarks, including heavy-tailed and multi-modal posteriors and a real-world application to computational neuroscience. Empirical results show that PAI succeeds where previous methods catastrophically fail, with a small communication overhead.
Spectral divide-and-conquer MCMC for long stationary time series
University of Technology Sydney(悉尼科技大学);Human Technology Institute, University of Technology Sydney(悉尼科技大学人类技术研究所);Guanghua School of Management, Peking University(北京大学光华管理学院);Stockholm University(斯德哥尔摩大学);University of New South Wales(新南威尔士大学)
Mad Props: Parallelism in Markov Chain Monte Carlo Through the Lens of the Infinite Proposal Limit
Indiana University(印第安纳大学);University of California, Los Angeles(加州大学洛杉矶分校);Virginia Polytechnic Institute and State University(弗吉尼亚理工大学);Drexel University(德雷塞尔大学)
Evaluating uncertainties in electrochemical impedance spectra of solid oxide fuel cells
Jožef Stefan Institute(约热夫·斯特凡研究所);Jožef Stefan International Postgraduate School(约热夫·斯特凡国际研究生院);Commissariat à l’Énergie Atomique et aux Énergies Alternatives - CEA(法国原子能与替代能源委员会(CEA))
Distributed Bayesian Matrix Factorization with Limited Communication
Helsinki Institute for Information Technology HIIT, Department of Computer Science, Aalto University(赫尔辛基信息科技研究院 HIIT,计算机科学系,阿莱大学);Department of Informatics, University of Bergen(信息学院,卑尔根大学)
Multilevel Sequential Importance Sampling for Rare Event Estimation
稀有事件发生概率的估计是可靠性和风险评估中的一项重要任务。我们考虑的故障事件表示的极限状态函数,这取决于一个偏微分方程(PDE)的解决方案。由于偏微分方程的数值计算是昂贵的,估计这样的概率的失败,蒙特卡罗抽样是棘手的。可靠性分析中更有效的抽样方法,如子集模拟,很受欢迎,但如果PDE评估成本很高,则仍然不可行。在这篇文章中,我们开发了一种新的,高效的估计罕见事件的概率。我们的方法是基于序贯重要性采样器使用离散化的PDE为基础的极限状态函数具有不同的精度。一个双重的自适应算法,确保我们得到一个估计的基础上所需的离散化精度。与[Ullmann,Papaioannou 2015; SIAM/ASA J. Uncertain.数量。3(1):922-953],我们的估计克服了嵌套问题。在顺序重要性采样算法中,特别重要的是正确选择MCMC内核。而不是流行的自适应条件采样方法,我们提出了一种新的算法,使用独立的建议,从自适应构造的冯Mises-Fischer-Nakagami分布。该算法分别应用于1D和2D空间中的测试问题,并与多级子集模拟估计量和单级版本的序贯重要性抽样和子集模拟进行比较。