CIF: Small: Message Passing Networks

CIF：小型：消息传递网络

• 批准号: 1217043
• 负责人: Devavrat Shah
• 金额: $ 11万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-07-01 至 2014-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1217043&HistoricalAwards=false
• 关键词: CIF; Small; Message; Passing; Networks

The goal of this project is to develop foundations for message-passing algorithms, in the realm of probabilistic graphical models. The project will focus on three classes of problems in graphical models: (a) learning graphical models from observed data, (b) computing the mode of a graphical model, and (c) computing marginals of variables in a graphical model. The project will identify the strengths and limitations of the popular belief propagation algorithm for all three problems. In addition, the project will develop new class of efficient message-passing algorithms with provable performance guarantees by means of exploiting the geometry of the graphical model.Probabilistic graphical models have become a standard way to represent uncertainty succinctly in a wide variety of applications: communication and signal processing, computation, vision and image processing, bioinformatics, natural language processing, and more. The problems faced in these applications are largely The research outcome of this project will be folded in the course titled "Algorithms for Inference (6.438)" taught by the PI. The course is a popular entry level graduate course which also disseminates material online through MIT Open CourseWare and going forward, it may explore possibility of wider dissemination through MITx/EdX.

这个项目的目标是在概率图形模型领域开发消息传递算法的基础。该项目将侧重于图形模型中的三类问题：(a)从观测数据中学习图形模型，(b)计算图形模型的模式，以及(c)计算图形模型中变量的边际。该项目将确定流行的信念传播算法在这三个问题上的优势和局限性。此外，该项目将开发一类新的高效消息传递算法，通过利用图形模型的几何形状来提供可证明的性能保证。概率图形模型已经成为一种标准的方式来简洁地表示不确定性在各种各样的应用：通信和信号处理，计算，视觉和图像处理，生物信息学，自然语言处理，等等。在这些应用中所面临的问题在很大程度上是这个项目的研究成果将在PI教授的“算法推理（6.438）”课程中折叠。这门课程是一门受欢迎的入门级研究生课程，它也通过麻省理工学院开放课程在线传播材料，未来，它可能会探索通过MITx/EdX更广泛传播的可能性。