Approximate Message Passing Algorithms for Inference and Optimization

用于推理和优化的近似消息传递算法

• 批准号: 1769423
• 金额: --
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2016
• 资助国家: 英国
• 起止时间: 2016 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-1769423
• 关键词: Approximate; Message; Passing; Algorithms; Inference

Message-passing algorithms are used for probabilistic inference in a variety of applications including communications, computer vision, and machine learning. Recently, there has been much interest in applying approximations of these algorithms to problems such as sparse regression and compressed sensing, where the dependence graph of the variables is dense. Despite empirical success in these settings, we do not have a sound theoretical understanding of approximate message-passing (AMP) yet. This project aims to theoretically characterize conditions under which does approximate message-passing works well. The project will also investigate applications of AMP to new settings such as capacity-achieving codes, sparse approximation, and data compression. The project is relevant to multiple EPSRC research areas including, Digital signal processing, RF and microwave communications, and Statistics and Applied probability.

消息传递算法用于各种应用中的概率推理，包括通信，计算机视觉和机器学习。最近，人们对将这些算法的近似应用于诸如稀疏回归和压缩感知之类的问题产生了很大的兴趣，其中变量的依赖图是密集的。尽管在这些环境中取得了经验上的成功，但我们对近似消息传递（AMP）还没有一个合理的理论理解。这个项目的目的是从理论上描述近似消息传递工作良好的条件。该项目还将研究AMP在新环境中的应用，如容量实现代码，稀疏近似和数据压缩。该项目涉及多个EPSRC研究领域，包括数字信号处理，射频和微波通信，统计和应用概率。

项目成果

Modulated Sparse Superposition Codes for the Complex AWGN Channel

复杂 AWGN 信道的调制稀疏叠加码

• DOI: 10.1109/tit.2021.3081368
• 发表时间: 2021
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Hsieh K

Capacity-achieving sparse regression codes via spatial coupling

通过空间耦合实现容量稀疏回归代码

• DOI: 10.1109/itw.2018.8613392
• 发表时间: 2018
• 作者: Rush C

Near-Optimal Coding for Massive Multiple Access

大规模多路访问的近乎最优编码

• DOI: 10.1109/isit45174.2021.9518275
• 发表时间: 2021
• 作者: Hsieh K

Spatially Coupled Sparse Regression Codes: Design and State Evolution Analysis

空间耦合稀疏回归代码：设计和状态演化分析

• DOI: 10.1109/isit.2018.8437615
• 发表时间: 2018
• 作者: Hsieh K

Capacity-achieving Spatially Coupled Sparse Superposition Codes with AMP Decoding

通过 AMP 解码实现大容量空间耦合稀疏叠加码

• DOI: 10.1109/tit.2021.3083733
• 发表时间: 2021
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Rush, Cynthia;Hsieh, Kuan;Venkataramanan, Ramji
• 通讯作者: Venkataramanan, Ramji