CAREER: Entropy Geometry in Variational Inference Signal Processing

职业：变分推理信号处理中的熵几何

基本信息

批准号：
1053702
负责人：
John Walsh
金额：
$ 50万
依托单位：
Drexel University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2011
资助国家：
美国
起止时间：
2011-07-01 至 2017-06-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1053702&HistoricalAwards=false
关键词：
CAREER Entropy Geometry Variational Inference

项目摘要

The past decade has proven that variational approaches to approximate Bayesian inference holdthe key to pragmatic solutions to many signal processing problems previously thought to be fundamentally difficult. Important signal processing problems where the application of appropriatevariational approximate Bayesian inference techniques led to significant breakthroughs include the decoding of capacity approaching codes for noisy channels, underdetermined speech source separation, and distributed estimation over networks. These applications provide evidence that variational inference techniques have revolutionized the state of the art in signal processing because of their ability to provide high performance estimates at reasonable complexity and communication (equivalently, energy consumption) costs. However, the tradeoff between their performance and required complexity and communication, the very phenomenon leading to their widespread and growing adoption, remains incompletely understood.The underlying thesis of this project is that entropy & information geometry lies at the heartof the tradeo^ff between performance, complexity, and communication in variational inference basedsignal processing. The research being performed improves our understanding of entropy geometry,which primarily dictates the fundamental relationship between the performance of a collaborativeestimation algorithm and its communication cost. This research also develops the information geometric relationship between a variational inference signal processing technique's performance andcomplexity. Together, these insights allow algorithms for robust speech processing and collaborative estimation over networks to be developed that provide optimal performance at a tunable complexity and communication cost. In addition to its benefits in each of these areas, the work has a synergistic aspect in that it contributes directly to the creation of an overall design science forefficient distributed variational inference signal processing algorithms.

过去的十年证明，近似贝叶斯推论的变异方法是务实解决方案的关键，以解决以前认为从根本上困难的许多信号处理问题。重要的信号处理问题，在适当变化的近似贝叶斯推理技术导致重大突破的情况下，包括对嘈杂通道的能力接近代码的解码，不确定的语音源分离以及对网络的分布式估计。这些应用提供了证据表明，由于它们能够以合理的复杂性和沟通（等效地，能耗）成本提供高性能估算的能力，因此变异推理技术在信号处理中彻底改变了最新技术的状态。但是，他们的表现与所需的复杂性和沟通之间的权衡，导致其广泛采用和不断增长的现象尚不完全理解。该项目的潜在论点是，熵和信息几何形状在于性能，复杂性和沟通之间的贸易中，基于各种基于基于基于差异的量子信号量。进行的研究提高了我们对熵几何形状的理解，这主要决定了协作估计算法的性能与其通信成本之间的基本关系。这项研究还开发了变分推理信号处理技术的性能和复杂性之间的信息几何关系。这些见解共同允许开发针对网络的强大语音处理和协作估算的算法，以可调节的复杂性和通信成本提供最佳性能。除了其在这些领域的每个领域中的好处外，这项工作还具有协同的方面，因为它直接有助于创建整体设计科学前基的分布式变异信号处理算法。