CIF:Small:Model-Based Blind Demixing for Signal Processing and Machine Learning

CIF：Small：用于信号处理和机器学习的基于模型的盲解混

基本信息

批准号：
1718771
负责人：
Justin Romberg
金额：
$ 49.97万
依托单位：
Georgia Tech Research Corporation
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-09-01 至 2021-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1718771&HistoricalAwards=false
关键词：
CIF Small Model Based Blind

项目摘要

The research centers on novel numerical methods and supporting theory for the multichannel convolutive blind demixing (MCBD) problem, where the responses for a set of inter-related time-invariant systems are estimated by observing only their outputs. The MCBD problem arises in many well-known applications in signal processing and communications; one of our goals for this project is to provide a unified framework for solving these problems that has a firm algorithmic and theoretical foundation. The goals are to provide a fundamental analysis of the information theoretic limits of MCBD, along with scalable algorithms that operate with provable performance guarantee at or near these limits. New applications of the MCBD problem will also be explored in the area of machine learning. In particular, the investigators will study how solutions to the MCBD problem can be used as an efficient method for both for the initialization in training deep convolutional neural networks, and for solving inverse problems associated with generative models.The work will combine classical statistical approaches and modern optimization-based techniques for constrained inverse problems. Of particular interest is the role that structure plays on making the problem identifiable, and on the stability of the solutions when the observations are corrupted by noise. Scenarios where this structure comes from domain-specific knowledge will be considered, along with scenarios where the model is data-driven. The algorithms developed in the project will be validated on applications in astronomical imaging, neuroimaging, medical imaging, seismic imaging, underwater acoustics, and deep learning. The proposed research has direct relevance to next-generation array processing for massive MIMO communications, device-to-device communication for the Internet-of-Things, and new integrated circuit RF transmitters. The work also may open a new direction in parallel MRI. The research activities will be complemented by new graduate courses focusing on modern mathematical methods for the next generation of data scientists.

该研究的重点是多通道卷积盲解混（MCBD）问题的新颖数值方法和支持理论，其中一组相互关联的时不变系统的响应通过仅观察其输出来估计。 MCBD 问题出现在信号处理和通信领域的许多著名应用中；我们这个项目的目标之一是提供一个统一的框架来解决这些问题，该框架具有坚实的算法和理论基础。目标是提供对 MCBD 信息论限制的基本分析，以及在这些限制或接近这些限制的情况下以可证明的性能保证运行的可扩展算法。 MCBD 问题的新应用也将在机器学习领域进行探索。特别是，研究人员将研究如何将 MCBD 问题的解决方案用作训练深度卷积神经网络的初始化以及解决与生成模型相关的逆问题的有效方法。这项工作将结合经典的统计方法和用于约束反问题的现代基于优化的技术。特别令人感兴趣的是结构在使问题可识别以及当观察被噪声破坏时解决方案的稳定性方面所发挥的作用。将考虑此结构来自特定领域知识的场景，以及模型是数据驱动的场景。该项目开发的算法将在天文成像、神经成像、医学成像、地震成像、水下声学和深度学习的应用中得到验证。拟议的研究与大规模 MIMO 通信的下一代阵列处理、物联网的设备到设备通信以及新型集成电路射频发射器直接相关。这项工作也可能为并行 MRI 开辟新的方向。研究活动将得到新的研究生课程的补充，该课程专注于下一代数据科学家的现代数学方法。

项目成果

期刊论文数量（16）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Identifiability Conditions for Compressive Multichannel Blind Deconvolution

压缩多通道盲解卷积的可识别性条件

DOI：
10.1109/tsp.2020.3011804
发表时间：
2020-01-02
期刊：
IEEE Transactions on Signal Processing
影响因子：
5.4
作者：
S. Mulleti;Kiryung Lee;Yonina C. Eldar
通讯作者：
Yonina C. Eldar

Generalized Notions of Sparsity and Restricted Isometry Property. Part II: Applications

稀疏性和受限等距性质的广义概念。

DOI：
10.1007/s00041-020-09809-8
发表时间：
2021-04
期刊：
Journal of Fourier Analysis and Applications
影响因子：
1.2
作者：
Junge, Marius;Lee, Kiryung
通讯作者：
Lee, Kiryung

Entropy Estimates on Tensor Products of Banach Spaces and Applications to Low-Rank Recovery

Banach空间张量积的熵估计及其在低阶恢复中的应用

DOI：
10.1109/sampta45681.2019.9030989
发表时间：
2020-03
期刊：
2019 13th International conference on Sampling Theory and Applications (SampTA
影响因子：
0
作者：
Lee, Kiryung;Srinivasa, Rakshith Sharma;Junge, Marius;Romberg, Justin
通讯作者：
Romberg, Justin

Sample complexity bounds for localized sketching

局部草图的示例复杂性范围

DOI：
发表时间：
2020-01
期刊：
Proeedings of the International Workshop on Artificial Intelligence and Statistics
影响因子：
0
作者：
Srinivasa, Rakshith Sharma;Davenport, Mark;Romberg, Justin
通讯作者：
Romberg, Justin

Sub-NYQUIST Multichannel Blind Deconvolution

Sub-NYQUIST 多通道盲解卷积

DOI：
10.1109/icassp39728.2021.9413856
发表时间：
2021-06-06
期刊：
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
0
作者：
S. Mulleti;Kiryung Lee;Yonina C. Eldar
通讯作者：
Yonina C. Eldar