AF: Medium: Dropping Convexity: New Algorithms, Statistical Guarantees and Scalable Software for Non-convex Matrix Estimation

AF:中:降低凸性:用于非凸矩阵估计的新算法、统计保证和可扩展软件

基本信息

  • 批准号:
    1564000
  • 负责人:
  • 金额:
    $ 90.24万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2016
  • 资助国家:
    美国
  • 起止时间:
    2016-09-01 至 2022-08-31
  • 项目状态:
    已结题

项目摘要

An image from your camera is a matrix of numbers, but most matrices of numbers would not look like an image -- the matrix of numbers in an image reflect structure from the scene. Many applications of data analysis across science, engineering, and business can be viewed as taking a matrix of observations and fitting low-rank or otherwise structured matrices to explain their relationships. Image and video analysis is not the only example; the problem arises in structural analysis of social networks, divining user preferences for new products and services, and many other analysis tasks. As the scale and dimensionality of these problems increases, the data analyst is faced with a gap between rigor and scale: theoretically sound algorithms often have requirements (e.g. repeated/random access to data) that are feasible only on medium-scale datasets, and even then may not provide answers in "interactive time" (i.e. smallish time scales required for a human interactively analyzing data). Thus practice has turned towards methods that lack rigorous guarantees, but that are scalable and have been observed to provide decent approximation. This project aims to narrow this gap by two technical observations: (a) Recognizing that fast matrix inference necessitates non-convex algorithms, it focuses on developing a rigorous analysis of the same, and (b) by explicitly incorporating big-data architectures (out of core, and distributed multicore) in the algorithm design and statistical analysis stage itself. it focuses on several specific tasks, including pass-efficient low-rank approximation, minimizing general convex functions over the non-convex set of low-rank matrices, robust matrix estimation, and non-linear and kernel matrix settings. The project trains graduate students in the mathematical and computational development important for data analysis. The promise of big data can only be realized by scaling infrastructure with data to continue to provide statistically meaningful insights; this project aims to realize this promise for a large suite of matrix estimation problems.
来自相机的图像是一个数字矩阵,但大多数数字矩阵看起来并不像图像--图像中的数字矩阵反映了场景的结构。数据分析在科学、工程和商业领域的许多应用可以看作是获取观测矩阵,并拟合低等级或其他结构的矩阵来解释它们之间的关系。图像和视频分析并不是唯一的例子;这个问题出现在社交网络的结构分析、预测用户对新产品和服务的偏好以及许多其他分析任务中。随着这些问题的规模和维度的增加,数据分析师面临着严格和规模之间的差距:从理论上讲,健全的算法通常具有只有在中等规模的数据集上才可行的要求(例如,重复/随机访问数据),即使这样,也可能无法在“交互时间”(即人类交互分析数据所需的较小时间尺度)内提供答案。因此,实践转向了缺乏严格保证的方法,但这些方法是可扩展的,并已被观察到提供了像样的近似值。该项目旨在通过两项技术意见缩小这一差距:(A)认识到快速矩阵推理需要非凸算法,它侧重于开发对非凸算法的严格分析,以及(B)在算法设计和统计分析阶段本身明确纳入大数据体系结构(核外和分布式多核)。它集中于几个具体的任务,包括通过有效的低阶逼近,最小化低阶矩阵的非凸集上的一般凸函数,稳健的矩阵估计,以及非线性和核矩阵的设置。该项目对研究生进行数学和计算开发方面的培训,这对数据分析非常重要。大数据的承诺只能通过使用数据扩展基础设施以继续提供统计上有意义的见解来实现;该项目旨在为一大套矩阵估计问题实现这一承诺。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ 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 }}

Sujay Sanghavi其他文献

Stratospheric chlorine activation in the Arctic winters 1995/96–2001/02 derived from GOME OClO measurements
1995/96–2001/02 北极冬季平流层氯活化来自 GOME OClO 测量
  • DOI:
    10.1016/j.asr.2003.08.069
  • 发表时间:
    2004
  • 期刊:
  • 影响因子:
    2.6
  • 作者:
    S. Kühl;W. Wilms;S. Beirle;C. Frankenberg;M. Grzegorski;J. Hollwedel;F. Khokhar;Sarit Kraus;U. Platt;Sujay Sanghavi;C. V. Friedeburg;T. Wagner
  • 通讯作者:
    T. Wagner
Geometric Median (GM) Matching for Robust Data Pruning
用于稳健数据修剪的几何中值 (GM) 匹配
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Anish Acharya;I. Dhillon;Sujay Sanghavi
  • 通讯作者:
    Sujay Sanghavi
Serving content with unknown demand: the high-dimensional regime
  • DOI:
    10.1007/s11134-015-9443-0
  • 发表时间:
    2015-04-12
  • 期刊:
  • 影响因子:
    0.700
  • 作者:
    Sharayu Moharir;Javad Ghaderi;Sujay Sanghavi;Sanjay Shakkottai
  • 通讯作者:
    Sanjay Shakkottai
Learning Graphical Models for Hypothesis Testing
学习假设检验的图形模型
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
使用 Transformers 进行上下文学习:Softmax Attention 适应函数 Lipschitzness
  • DOI:
    10.48550/arxiv.2402.11639
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Liam Collins;Advait Parulekar;Aryan Mokhtari;Sujay Sanghavi;Sanjay Shakkottai
  • 通讯作者:
    Sanjay Shakkottai

Sujay Sanghavi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('Sujay Sanghavi', 18)}}的其他基金

Collaborative Research: EnCORE: Institute for Emerging CORE Methods in Data Science
合作研究:EnCORE:数据科学新兴核心方法研究所
  • 批准号:
    2217069
  • 财政年份:
    2022
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant
HDR TRIPODS: UT Austin Institute on the Foundations of Data Science
HDR TRIPODS:UT Austin 数据科学基础研究所
  • 批准号:
    1934932
  • 财政年份:
    2019
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant
CIF: Medium: Collaborative Research: New Approaches to Robustness in High-Dimensions
CIF:中:协作研究:高维鲁棒性的新方法
  • 批准号:
    1302435
  • 财政年份:
    2013
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant
CAREER: Networks and Statistical Inference: New Connections and Algorithms
职业:网络和统计推断:新连接和算法
  • 批准号:
    0954059
  • 财政年份:
    2010
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant
NetSE: Small: Social Networks in the Real World: From Sensing to Structure Analysis
NetSE:小型:现实世界中的社交网络:从感知到结构分析
  • 批准号:
    1017525
  • 财政年份:
    2010
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
NeTS: Medium: Collaborative Research: Shaping, Learning and Optimizing Dynamic Networks
NeTS:媒介:协作研究:塑造、学习和优化动态网络
  • 批准号:
    0964391
  • 财政年份:
    2010
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant

相似海外基金

RII Track-4:@NASA: Bluer and Hotter: From Ultraviolet to X-ray Diagnostics of the Circumgalactic Medium
RII Track-4:@NASA:更蓝更热:从紫外到 X 射线对环绕银河系介质的诊断
  • 批准号:
    2327438
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: Topological Defects and Dynamic Motion of Symmetry-breaking Tadpole Particles in Liquid Crystal Medium
合作研究:液晶介质中对称破缺蝌蚪粒子的拓扑缺陷与动态运动
  • 批准号:
    2344489
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: AF: Medium: The Communication Cost of Distributed Computation
合作研究:AF:媒介:分布式计算的通信成本
  • 批准号:
    2402836
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing Grant
Collaborative Research: AF: Medium: Foundations of Oblivious Reconfigurable Networks
合作研究:AF:媒介:遗忘可重构网络的基础
  • 批准号:
    2402851
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Continuing 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:
    2403122
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
  • 批准号:
    2403134
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: CyberTraining: Implementation: Medium: Training Users, Developers, and Instructors at the Chemistry/Physics/Materials Science Interface
协作研究:网络培训:实施:媒介:在化学/物理/材料科学界面培训用户、开发人员和讲师
  • 批准号:
    2321102
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: CyberTraining: Implementation: Medium: Transforming the Molecular Science Research Workforce through Integration of Programming in University Curricula
协作研究:网络培训:实施:中:通过将编程融入大学课程来改变分子科学研究人员队伍
  • 批准号:
    2321045
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: CyberTraining: Implementation: Medium: Training Users, Developers, and Instructors at the Chemistry/Physics/Materials Science Interface
协作研究:网络培训:实施:媒介:在化学/物理/材料科学界面培训用户、开发人员和讲师
  • 批准号:
    2321103
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
Collaborative Research: CPS: Medium: Automating Complex Therapeutic Loops with Conflicts in Medical Cyber-Physical Systems
合作研究:CPS:中:自动化医疗网络物理系统中存在冲突的复杂治疗循环
  • 批准号:
    2322534
  • 财政年份:
    2024
  • 资助金额:
    $ 90.24万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了