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.

研究的研究集中在多通道综合盲盲（MCBD）问题的新型数值方法和支持理论中，其中仅通过观察其输出来估算一组相互关联的时间不变系统的响应。 MCBD问题在信号处理和通信中的许多众所周知的应用中产生。该项目的目标之一是提供一个统一的框架来解决这些具有牢固算法和理论基础的问题。目标是对MCBD的信息理论限制以及可扩展的算法提供基本分析，这些算法在这些限制或接近这些限制下可证明性能保证。 MCBD问题的新应用也将在机器学习领域进行探讨。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初始化的有效方法，以及解决与生成模型相关的逆问题。该工作将结合经典的统计方法和基于现代优化的技术来解决约束逆问题。特别有趣的是结构在使问题可识别的作用以及当观测因噪声破坏时解决方案的稳定性。该结构来自特定于领域的知识的方案以及模型是数据驱动的方案。该项目中开发的算法将在天文成像，神经影像，医学成像，地震成像，水下声学和深度学习中的应用中进行验证。拟议的研究与下一代阵列处理直接相关，以进行大规模的MIMO通信，设备到设备的通信以及新的集成电路RF RF发射机。这项工作还可以在平行MRI中打开一个新的方向。研究活动将由新的研究生课程进行补充，该课程的重点是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）

Fast and Guaranteed Blind Multichannel Deconvolution Under a Bilinear System Model

DOI：
10.1109/tit.2018.2840711
发表时间：
2016-10
期刊：
IEEE Transactions on Information Theory
影响因子：
2.5
作者：
Kiryung Lee;Ning Tian;J. Romberg
通讯作者：
Kiryung Lee;Ning Tian;J. Romberg

Sub-NYQUIST Multichannel Blind Deconvolution

DOI：
10.1109/icassp39728.2021.9413856
发表时间：
2021-06
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：
S. Mulleti;Kiryung Lee;Yonina C. Eldar

Sample complexity bounds for localized sketching

局部草图的示例复杂性范围

DOI：
发表时间：
2020
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

Generalized notions of sparsity and restricted isometry property. Part I: a unified framework