权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

CAREER: Guaranteed Nonconvex Optimization for High-Dimensional Learning

职业：高维学习的有保证的非凸优化

基本信息

批准号：
1846369
负责人：
Mahdi Soltanolkotabi
金额：
$ 54.93万
依托单位：
University of Southern California
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-02-01 至 2025-01-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1846369&HistoricalAwards=false
关键词：
CAREER Guaranteed Nonconvex Optimization Dimensional

项目摘要

Contemporary nonconvex learning approaches in signal processing and machine learning are revolutionizing our ability to process data in their natural form, bringing transformative changes to modern life ranging from web searches and social networks to healthcare, commerce, and imaging. Despite wide empirical success in applications, these learning schemes lack a clear mathematical foundation that can enable not only rigorous performance analysis but can guide system designs based on an understanding of what would work, when and why. This project aims to develop a unified framework to design and analyze efficient nonconvex optimization algorithms. The resulting signal estimation and learning algorithms will be deployed in novel applications aimed at learning understandable models from data, which in turn will allow for better systems that can acquire data faster and at higher resolution and quality. Components from this project are integrated into an advanced graduate class and select results will serve to motivate K-12 students to pursue careers in STEM (Science, Technology, Engineering and Math).In this project, the investigator studies a family of iterative algorithms for nonconvex data fitting problems that arise in modern signal processing and artificial intelligence, such as phaseless imaging and neural network training. The overarching goal of the project is to understand when these algorithms converge to globally optimal solutions and to characterize their behavior and convergence rate in terms of key quantities such as the number of data samples/observations, prior knowledge about the model, initialization accuracy, etc. The theoretical investigations utilize techniques from high-dimensional probability, statistics, optimization and nonlinear dynamics in control. The theoretical analysis guides the design of more reliable learning algorithms that can seamlessly scale to massive data sizes and are robust to node failures that arise in modern distributed computing environments.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

信号处理和机器学习中的当代非凸学习方法正在彻底改变我们处理自然形式数据的能力，为现代生活带来革命性的变化，从网络搜索和社交网络到医疗保健、商业和成像。尽管在应用中取得了广泛的经验成功，但这些学习方案缺乏明确的数学基础，该基础不仅可以进行严格的性能分析，而且可以基于对什么是有效的、何时有效以及为什么有效的理解来指导系统设计。该项目旨在开发一个统一的框架来设计和分析高效的非凸优化算法。由此产生的信号估计和学习算法将部署在旨在从数据中学习可理解的模型的新颖应用中，这反过来又将允许更好的系统能够更快地以更高的分辨率和质量获取数据。该项目的组成部分被整合到高级研究生课程中，选定的结果将有助于激励 K-12 学生追求 STEM（科学、技术、工程和数学）职业。在该项目中，研究人员研究了一系列迭代算法，用于解决现代信号处理和人工智能（例如无相成像和神经网络训练）中出现的非凸数据拟合问题。该项目的总体目标是了解这些算法何时收敛到全局最优解，并根据数据样本/观测数量、模型先验知识、初始化精度等关键量来表征其行为和收敛速度。理论研究利用高维概率、统计、优化和控制中的非线性动力学技术。理论分析指导设计更可靠的学习算法，这些算法可以无缝扩展到海量数据规模，并且对现代分布式计算环境中出现的节点故障具有鲁棒性。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（37）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Structured Signal Recovery From Quadratic Measurements: Breaking Sample Complexity Barriers via Nonconvex Optimization

DOI：
10.1109/tit.2019.2891653
发表时间：
2017-02
期刊：
IEEE Transactions on Information Theory
影响因子：
2.5
作者：
M. Soltanolkotabi
通讯作者：
M. Soltanolkotabi

Understanding Overparameterization in Generative Adversarial Networks

DOI：
发表时间：
2021-04
期刊：
ArXiv
影响因子：
0
作者：
Y. Balaji;M. Sajedi;N. Kalibhat;Mucong Ding;Dominik Stöger;M. Soltanolkotabi;S. Feizi
通讯作者：
Y. Balaji;M. Sajedi;N. Kalibhat;Mucong Ding;Dominik Stöger;M. Soltanolkotabi;S. Feizi

Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory

DOI：
10.48550/arxiv.2307.00497
发表时间：
2023-07
期刊：
ArXiv
影响因子：
0
作者：
Sara Babakniya;Zalan Fabian;Chaoyang He;M. Soltanolkotabi;S. Avestimehr
通讯作者：
Sara Babakniya;Zalan Fabian;Chaoyang He;M. Soltanolkotabi;S. Avestimehr

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks

DOI：
10.18653/v1/2022.findings-naacl.13
发表时间：
2021-04
期刊：
影响因子：
0
作者：
Bill Yuchen Lin;Chaoyang He;ZiHang Zeng;Hulin Wang;Yufen Huang;M. Soltanolkotabi;Xiang Ren;S. Avestimehr
通讯作者：
Bill Yuchen Lin;Chaoyang He;ZiHang Zeng;Hulin Wang;Yufen Huang;M. Soltanolkotabi;Xiang Ren;S. Avestimehr

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?