Collaborative Research: CIF: Small: Deep Sparse Models: Analysis and Algorithms
合作研究:CIF:小型:深度稀疏模型:分析和算法
基本信息
- 批准号:2008460
- 负责人:
- 金额:$ 20.55万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2020
- 资助国家:美国
- 起止时间:2020-07-01 至 2022-09-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Deep convolutional neural networks are a class of mathematical models that provide a variety of machine learning tools with impressive success, often obtaining state-of-the-art results across different fields. Yet, their theoretical understanding and the fundamental ideas behind these algorithms have remained elusive. These questions are essential to recognize and characterize their limitations, to provide guarantees for their performance, and even to develop and engineer improved practical models. A promising approach to obtain this understanding is to make assumptions about the class of samples on which these models are deployed (e.g., so that these are "simple enough") with the intention of providing theoretical insights about them. Further understanding of this 'multi-layered convolutional sparse model' is what this project seeks accomplish, broadening the understanding of its related optimization and learning problems, and shedding light on deep learning methodologies.This project proposes to advance the state of the art in generalized sparse models of different numbers of layers, focusing on both inference and learning problems. Provable and efficient optimization methods will be derived for the inverse problems associated with multilayer sparse models by relying on new results in proximal gradient and subgradient descent methods. This proposal will further extend the formulation of the pursuit to other settings, increasing stability and robustness to the choice of parameters and to outliers. Furthermore, efficient algorithms for the corresponding unsupervised learning problem will be proposed and analyzed. Questions of sample complexity and generalization bounds will in turn be studied in supervised learning settings. Throughout this project, the resulting algorithms will be studied in terms of their relation to specific convolutional network architectures. The project brings together combined expertise in signal processing, dictionary learning, machine learning, and the design, analysis and implementation of optimization methods for large-scale problems.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.
深度卷积神经网络是一类数学模型,它提供了各种机器学习工具,取得了令人印象深刻的成功,经常在不同的领域获得最先进的结果。然而,他们的理论理解和这些算法背后的基本思想仍然难以捉摸。这些问题对于认识和描述它们的局限性、为它们的性能提供保证、甚至开发和设计改进的实用模型都是至关重要的。要获得这种理解,一个有希望的方法是对部署这些模型的样本类别做出假设(例如,使这些模型“足够简单”),目的是提供关于它们的理论见解。进一步理解这种“多层卷积稀疏模型”,拓宽了对其相关优化和学习问题的理解,并揭示了深度学习方法。本项目旨在促进不同层数的广义稀疏模型的发展,重点研究推理和学习问题。利用近邻梯度法和次梯度下降法的新结果,将得到与多层稀疏模型相关的反问题的可证明的、有效的优化方法。这一提议将进一步将追逐的提法扩展到其他环境,增加对参数选择和对异常值的稳定性和稳健性。此外,还将针对相应的无监督学习问题提出并分析有效的算法。样本复杂性和泛化范围的问题将依次在监督学习环境中进行研究。在整个项目中,将根据它们与特定卷积网络体系结构的关系来研究得到的算法。该项目汇集了信号处理、词典学习、机器学习以及针对大规模问题的优化方法的设计、分析和实施方面的综合专业知识。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势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(7)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Learning Approach For Fast Approximate Matrix Factorizations
- DOI:10.1109/icassp43922.2022.9747165
- 发表时间:2022-05
- 期刊:
- 影响因子:0
- 作者:Haiyan Yu;Zhen Qin;Zhihui Zhu
- 通讯作者:Haiyan Yu;Zhen Qin;Zhihui Zhu
Recovery and Generalization in Over-Realized Dictionary Learning
- DOI:
- 发表时间:2020-06
- 期刊:
- 影响因子:0
- 作者:Jeremias Sulam;Chong You;Zhihui Zhu
- 通讯作者:Jeremias Sulam;Chong You;Zhihui Zhu
A Geometric Analysis of Neural Collapse with Unconstrained Features
- DOI:
- 发表时间:2021-05
- 期刊:
- 影响因子:0
- 作者:Zhihui Zhu;Tianyu Ding;Jinxin Zhou;Xiao Li;Chong You;Jeremias Sulam;Qing Qu
- 通讯作者:Zhihui Zhu;Tianyu Ding;Jinxin Zhou;Xiao Li;Chong You;Jeremias Sulam;Qing Qu
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
- DOI:
- 发表时间:2021-03
- 期刊:
- 影响因子:0
- 作者:Sheng Liu;Xiao Li;Yuexiang Zhai;Chong You;Zhihui Zhu;C. Fernandez‐Granda;Qing Qu
- 通讯作者:Sheng Liu;Xiao Li;Yuexiang Zhai;Chong You;Zhihui Zhu;C. Fernandez‐Granda;Qing Qu
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
- DOI:
- 发表时间:2020-06
- 期刊:
- 影响因子:0
- 作者:Chong You;Zhihui Zhu;Qing Qu;Yi Ma
- 通讯作者:Chong You;Zhihui Zhu;Qing Qu;Yi Ma
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Zhihui Zhu其他文献
Effects of different interventions on internet addiction: A meta-analysis of random controlled trials
- DOI:
10.1016/j.jad.2022.06.013 - 发表时间:
2022 - 期刊:
- 影响因子:
- 作者:
Xueqing Zhang;Jianghui Zhang;Kexin Zhang;Juan Ren;Xiaoyan Lu;Tianli Wang;Huayu Yang;Haiyun Guo;Guojing Yuan;Zhihui Zhu;Jiahu Hao;Ying Sun;Puyu Su;Linsheng Yang;Zhihua Zhang - 通讯作者:
Zhihua Zhang
Cascade nanozymes based on the “butterfly effect” for enhanced starvation therapy through the regulation of autophagy
- DOI:
10.1039/d2bm00595f - 发表时间:
2022 - 期刊:
- 影响因子:6.6
- 作者:
Hanchun Yao;Xiaobao Gong;Meilin Geng;Songchao Duan;Pan Qiao;Fangfang Sun;Zhihui Zhu;Bin Du - 通讯作者:
Bin Du
GM1 up-regulates Ubiquilin 1 expression in human neuroblastoma cells and rat cortical neurons
GM1 上调人神经母细胞瘤细胞和大鼠皮质神经元中泛素 1 的表达
- DOI:
10.1016/j.neulet.2006.08.005 - 发表时间:
2006 - 期刊:
- 影响因子:2.5
- 作者:
Zhonghua Liu;Y. Ruan;W. Yue;Zhihui Zhu;T. Hartmann;K. Beyreuther;Dai Zhang - 通讯作者:
Dai Zhang
Fabrication of organic-inorganic double-walled (ER@EC/SiOsub2/sub) microcapsules via biomimetic mineralization for self-healing cementitious materials
通过仿生矿化制备用于自修复胶凝材料的有机 - 无机双层壁(ER@EC/SiO₂)微胶囊
- DOI:
10.1016/j.compositesb.2025.112355 - 发表时间:
2025-06-01 - 期刊:
- 影响因子:14.200
- 作者:
Xuanzhe Zhang;Xianfeng Wang;Zhihui Zhu;Wentao Yang;Guangming Zhu;Feng Xing - 通讯作者:
Feng Xing
Traffic function damage risk assessment of high-speed railway simply-supported bridges considering the total probability information expression of near-fault pulse-like earthquakes
考虑近断层脉冲型地震总概率信息表达的高速铁路简支梁桥行车功能损伤风险评估
- DOI:
10.1016/j.ress.2025.111241 - 发表时间:
2025-10-01 - 期刊:
- 影响因子:11.000
- 作者:
Gaoyang Zhou;Zhihui Zhu;Weiqi Zheng;Kun Wang - 通讯作者:
Kun Wang
Zhihui Zhu的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Zhihui Zhu', 18)}}的其他基金
Collaborative Research: RI: Medium: Principles for Optimization, Generalization, and Transferability via Deep Neural Collapse
合作研究:RI:中:通过深度神经崩溃实现优化、泛化和可迁移性的原理
- 批准号:
2312840 - 财政年份:2023
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Small: Deep Sparse Models: Analysis and Algorithms
合作研究:CIF:小型:深度稀疏模型:分析和算法
- 批准号:
2240708 - 财政年份:2022
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Medium: Structured Inference and Adaptive Measurement Design in Indirect Sensing Systems
合作研究:CIF:媒介:间接传感系统中的结构化推理和自适应测量设计
- 批准号:
2241298 - 财政年份:2022
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Medium: Structured Inference and Adaptive Measurement Design in Indirect Sensing Systems
合作研究:CIF:媒介:间接传感系统中的结构化推理和自适应测量设计
- 批准号:
2106881 - 财政年份:2021
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: CIF: Medium: Snapshot Computational Imaging with Metaoptics
合作研究:CIF:Medium:Metaoptics 快照计算成像
- 批准号:
2403122 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs
合作研究:CIF-Medium:图上的隐私保护机器学习
- 批准号:
2402815 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Small: Mathematical and Algorithmic Foundations of Multi-Task Learning
协作研究:CIF:小型:多任务学习的数学和算法基础
- 批准号:
2343599 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Small: Mathematical and Algorithmic Foundations of Multi-Task Learning
协作研究:CIF:小型:多任务学习的数学和算法基础
- 批准号:
2343600 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs
合作研究:CIF-Medium:图上的隐私保护机器学习
- 批准号:
2402817 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs
合作研究:CIF-Medium:图上的隐私保护机器学习
- 批准号:
2402816 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: NSF-AoF: CIF: Small: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
合作研究:NSF-AoF:CIF:小型:用于集成传感和通信的人工智能辅助波形和波束成形设计
- 批准号:
2326622 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Medium: Snapshot Computational Imaging with Metaoptics
合作研究:CIF:Medium:Metaoptics 快照计算成像
- 批准号:
2403123 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: NSF-AoF: CIF: Small: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
合作研究:NSF-AoF:CIF:小型:用于集成传感和通信的人工智能辅助波形和波束成形设计
- 批准号:
2326621 - 财政年份:2024
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Small: Versatile Data Synchronization: Novel Codes and Algorithms for Practical Applications
合作研究:CIF:小型:多功能数据同步:实际应用的新颖代码和算法
- 批准号:
2312872 - 财政年份:2023
- 资助金额:
$ 20.55万 - 项目类别:
Standard Grant