I present a parallel algorithm for exact probabilistic inference in Bayesian networks. For polytree networks with n variables, the worst-case time complexity is O(log n) on a CREW PRAM (concurrent-read, exclusive-write parallel random-access machine) with n processors, for any constant number of evidence variables. For arbitrary networks, the time complexity is O(r^{3w}*log n) for n processors, or O(w*log n) for r^{3w}*n processors, where r is the maximum range of any variable, and w is the induced width (the maximum clique size), after moralizing and triangulating the network.
Fast Parallel Exact Inference on Bayesian Networks: Poster
The University of Western Australia(西澳大利亚大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Hong Kong University of Science and Technology(香港科技大学)
When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
Harvard University(哈佛大学);Center for Brain Science, Harvard University(哈佛大学脑科学中心);Kempner Institute(坎普纳研究所);Edmond and Lily Safra Center for Brain Sciences, Hebrew University of Jerusalem(耶路撒冷希伯来大学埃德蒙和莉莉·萨夫拉脑科学中心)
A Parallel Technique for Multi-objective Bayesian Global Optimization: Using a Batch Selection of Probability of Improvement
University of Applied Sciences Upper Austria(上奥地利应用科学大学);Central South University(中南大学)
贝叶斯全局优化(BGO)是一种有效的代理辅助技术,涉及昂贵的评估问题。一种并行技术可用于在一次迭代中对真昂贵的目标函数进行并行评估,以提高执行时间。一种有效且直接的方法是设计一个采集函数,该采集函数可以在一次迭代中评估多个解决方案而不是单个点/解决方案的性能。针对多目标贝叶斯全局优化(MOBGO)问题,考虑多点间的协方差性,提出了5种多点批量\emph{Probability of Improvement}(PoI)算法(q-PoI).所有建议的q-PoIs的精确计算公式和蒙特卡罗近似算法提供。基于与Pareto前沿相关的多个点的分布,研究了五个q-PoIs的位置依赖行为。此外,五个q-PoIs相比,其他九个国家的最先进的,最近提出的批处理MOBGO算法的20个生物目标的基准。在不同的基准上进行了实证实验,以证明两种贪婪q-PoIs($\kpoi_{\mbox{best}}$和$\kpoi_{\mbox{all}}$)在低维问题上的有效性,以及两种探索性q-PoIs($\kpoi_{\mbox{one}}$和$\kpoi_{\mbox{worst}}$)在具有难以近似Pareto前沿边界的高维问题上的有效性。
Surrogate-assisted parallel tempering for Bayesian neural learning
University of New South Wales(新南威尔士大学);The University of Sydney(悉尼大学);Indian Institute of Technology Guwahati(印度理工学院古瓦哈提分校);SRM Institute of Science and Technology(SRM科学技术学院);Indian Institute of Technology Delhi(印度理工学院德里分校)