Online Dictionary Learning for Dependent and Multimodal Data Samples: Convergence, Complexity, and Applications
相关和多模态数据样本的在线字典学习:收敛性、复杂性和应用
基本信息
- 批准号:2206296
- 负责人:
- 金额:$ 30万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-09-01 至 2025-08-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
One of the remarkable human capabilities is the ability to extract essential patterns from a constantly evolving stream of information that shapes everyday decision-making. Online dictionary learning (ODL) is a mathematical formulation that emulates the human ability to extract patterns in real time. ODL has found fruitful applications in various domains such as text analysis, image reconstruction and denoising, medical imaging, and bioinformatics. However, existing theories and algorithms for ODL are facing significant challenges in coping with modern streaming data. This project will advance both the theoretical understanding and algorithmic capacities of existing ODL methods. More specifically, the project will address challenges in handling streaming data with multi-modal attributes, partial labels for further classification or inference tasks, and heterogeneous structure in the form of networks. This project will also involve interdisciplinary collaboration and provide research opportunities for students at all levels. The project aims to advance the theory and algorithms of ODL in the following aspects: 1) Obtain the worst-case rate of convergence and iteration complexity of generalized ODL algorithms to stationary points for a stream of structured signals under Markovian dependence; 2) Devise supervised ODL algorithms for learning class-discriminating dictionaries from labeled streaming data with provable convergence guarantees and rate of convergence; 3) Use the theory and algorithm for supervised ODL with tensor-valued signals to develop methods of supervised and temporal network dictionary learning, where the former will learn discriminative basis subgraphs from network data for network classification and denoising applications and the latter will learn basis subgraphs and their time-evolution for reconstructing given temporal or multilayer networks. A key element is the development of stochastic majorization-minimization type algorithms that can handle complex surrogate functions depending on data type using block-minimization and regularization techniques. This project will also provide students with research experiences in optimization, machine learning, and network science. Specific topics for undergraduate research experience will include generating a repository of optimal network dictionaries for various real-world networks, network-level regression and inference experiments with biological networks, and temporal brain network analysis.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.
人类最了不起的能力之一就是能够从不断演变的信息流中提取基本模式,这些信息流影响着日常决策。在线词典学习(ODL)是一种数学公式,它模拟了人类在真实的时间内提取模式的能力。ODL在文本分析、图像重建和去噪、医学成像和生物信息学等领域都有着丰富的应用。然而,现有的ODL理论和算法在处理现代流数据时面临着重大挑战。该项目将推进现有ODL方法的理论理解和算法能力。更具体地说,该项目将解决处理具有多模态属性的流数据,用于进一步分类或推理任务的部分标签以及网络形式的异构结构的挑战。该项目还将涉及跨学科合作,并为各级学生提供研究机会。本项目的主要目标是在以下几个方面推进ODL的理论和算法:1)获得广义ODL算法在马尔可夫依赖下到达稳定点的最坏情况下的收敛速度和迭代复杂度; 2)设计有监督的ODL算法,用于从标记的流数据中学习具有可证明的收敛保证和收敛速度的类别区分字典; 3)使用张量值信号的监督ODL的理论和算法来开发监督和时态网络字典学习的方法,其中前者将从网络数据中学习用于网络分类和去噪应用的判别基子图,后者将学习基子图及其时间演化以重建给定的时态或多层网络。一个关键因素是随机优化最小化类型的算法,可以处理复杂的代理函数依赖于数据类型,使用块最小化和正则化技术的发展。该项目还将为学生提供优化,机器学习和网络科学方面的研究经验。本科生研究经验的具体主题将包括为各种真实世界的网络生成最佳网络字典库,生物网络的网络级回归和推理实验,以及时间脑网络分析。该奖项反映了NSF的法定使命,并被认为值得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来支持。
项目成果
期刊论文数量(4)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
具有相关数据的约束非凸优化的一阶方法的收敛性
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Ahmet Alacaoglu;Hanbaek Lyu
- 通讯作者:Hanbaek Lyu
Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning
- DOI:10.48550/arxiv.2306.02420
- 发表时间:2023-06
- 期刊:
- 影响因子:0
- 作者:Dohyun Kwon;Hanbaek Lyu
- 通讯作者:Dohyun Kwon;Hanbaek Lyu
Sampling random graph homomorphisms and applications to network data analysis
随机图同态采样及其在网络数据分析中的应用
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:6
- 作者:Hanbaek Lyu, Facundo Mémoli
- 通讯作者:Hanbaek Lyu, Facundo Mémoli
{{
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 }}
Hanbaek Lyu其他文献
Supervised low-rank semi-nonnegative matrix factorization with frequency regularization for forecasting spatio-temporal data
用于预测时空数据的频率正则化监督低秩半非负矩阵分解
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:2.5
- 作者:
Keunsu Kim;Hanbaek Lyu;Jinsu Kim;Jae - 通讯作者:
Jae
Chromatic Number, Induced Cycles, and Non-separating Cycles
- DOI:
10.1007/s00373-020-02187-4 - 发表时间:
2020-05-27 - 期刊:
- 影响因子:0.600
- 作者:
Hanbaek Lyu - 通讯作者:
Hanbaek Lyu
Clustering in the Three and Four Color Cyclic Particle Systems in One Dimension
一维三色和四色循环粒子系统的聚类
- DOI:
- 发表时间:
2017 - 期刊:
- 影响因子:0
- 作者:
E. Foxall;Hanbaek Lyu - 通讯作者:
Hanbaek Lyu
Double Jump Phase Transition in a Soliton Cellular Automaton
孤子元胞自动机中的双跳相变
- DOI:
10.1093/imrn/rnaa166 - 发表时间:
2017 - 期刊:
- 影响因子:1
- 作者:
Lionel Levine;Hanbaek Lyu;John Pike - 通讯作者:
John Pike
Stochastic regularized majorization-minimization with weakly convex and multi-convex surrogates
- DOI:
- 发表时间:
2022-01 - 期刊:
- 影响因子:0
- 作者:
Hanbaek Lyu - 通讯作者:
Hanbaek Lyu
Hanbaek Lyu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('Hanbaek Lyu', 18)}}的其他基金
Combinatorial and Probabilistic Approaches to Oscillator and Clock Synchronization
振荡器和时钟同步的组合和概率方法
- 批准号:
2232241 - 财政年份:2021
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Combinatorial and Probabilistic Approaches to Oscillator and Clock Synchronization
振荡器和时钟同步的组合和概率方法
- 批准号:
2010035 - 财政年份:2020
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
相似海外基金
Distributed video coding and deep learning using convolutional sparse dictionary generated with large scale datasets
使用大规模数据集生成的卷积稀疏字典进行分布式视频编码和深度学习
- 批准号:
23K11159 - 财政年份:2023
- 资助金额:
$ 30万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Applications of Sparse Representation, Low Rank Approximation and Dictionary Learning to Image Processing, Pattern Recognition and Computer Vision
稀疏表示、低秩近似和字典学习在图像处理、模式识别和计算机视觉中的应用
- 批准号:
RGPIN-2016-05467 - 财政年份:2021
- 资助金额:
$ 30万 - 项目类别:
Discovery Grants Program - Individual
Magnetic Resonance Imaging Data Acquisition Acceleration and Feature Detection with Dictionary Learning
通过字典学习进行磁共振成像数据采集加速和特征检测
- 批准号:
565721-2021 - 财政年份:2021
- 资助金额:
$ 30万 - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Master's
A study on online dictionary use and vocabulary choices in L2 learning using smartphone video recording
利用智能手机视频录制进行二语学习中在线词典使用和词汇选择的研究
- 批准号:
21K18375 - 财政年份:2021
- 资助金额:
$ 30万 - 项目类别:
Grant-in-Aid for Challenging Research (Exploratory)
Multi-Modal Dictionary Learning for Smart City Operation and Management
智慧城市运营管理的多模态词典学习
- 批准号:
LP190100079 - 财政年份:2020
- 资助金额:
$ 30万 - 项目类别:
Linkage Projects
Applications of Sparse Representation, Low Rank Approximation and Dictionary Learning to Image Processing, Pattern Recognition and Computer Vision
稀疏表示、低秩近似和字典学习在图像处理、模式识别和计算机视觉中的应用
- 批准号:
RGPIN-2016-05467 - 财政年份:2020
- 资助金额:
$ 30万 - 项目类别:
Discovery Grants Program - Individual
Decoding of motor signals using non-linear generalization of sparse coding and dictionary learning
使用稀疏编码和字典学习的非线性推广对运动信号进行解码
- 批准号:
18KK0308 - 财政年份:2019
- 资助金额:
$ 30万 - 项目类别:
Fund for the Promotion of Joint International Research (Fostering Joint International Research (A))
How recent changes in dictionary types have affected the lookup behavior and learning outcomes of college English learners?
最近词典类型的变化如何影响大学英语学习者的查找行为和学习成果?
- 批准号:
19K00777 - 财政年份:2019
- 资助金额:
$ 30万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Applications of Sparse Representation, Low Rank Approximation and Dictionary Learning to Image Processing, Pattern Recognition and Computer Vision
稀疏表示、低秩近似和字典学习在图像处理、模式识别和计算机视觉中的应用
- 批准号:
RGPIN-2016-05467 - 财政年份:2019
- 资助金额:
$ 30万 - 项目类别:
Discovery Grants Program - Individual
Cross-modal signal estimation by coupled dictionary learning and its aaplication to non-contact sensing
耦合字典学习的跨模态信号估计及其在非接触传感中的应用
- 批准号:
19K04429 - 财政年份:2019
- 资助金额:
$ 30万 - 项目类别:
Grant-in-Aid for Scientific Research (C)