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
基本信息
- 批准号:1302435
- 负责人:
- 金额:$ 69.54万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2013
- 资助国家:美国
- 起止时间:2013-07-01 至 2019-06-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Rapid development of large-scale data collection technology hasignited research into high-dimensional machine learning. Forinstance, the problem of designing recommender systems, such as thoseused by Amazon, Netflix and other on-line companies, involvesanalyzing large matrices that describe users' behavior in pastsituations. In sociology, researchers are interested in fittingnetworks to large-scale data sets, involving hundreds or thousands ofindividuals. In medical imaging, the goal is to reconstructcomplicated phenomena (e.g., brain images; videos of a beating heart)based on a minimal number of incomplete and possibly corruptedmeasurements. Motivated by such applications, the goal of thisresearch is to develop and analyze models and algorithms forextracting relevant structure from such high-dimensional data sets ina robust and scalable fashion.The research leverages tools from convex optimization, signalprocessing, and robust statistics. It consists of three main thrusts:(1) Model restrictiveness: Successful methods for high-dimensionaldata exploit low-dimensional structure; however, many real-worldproblems fall outside the scope of existing models. This proposalsignificantly extends the basic set-up by allowing for multiplestructures, leading to computationally efficient algorithms whileeliminating negative effects of model mismatch. (2) Non-ideal data:Missing data are prevalent in real-world problems, and can cause majorbreakdowns in standard algorithms for high-dimensional data. Thesecond thrust devises relaxations and greedy approaches for thesenon-convex problems. (3) Arbitrary Outliers: Gross errors can arisefor various reasons, including fault-prone sensors and manipulativeagents. The third thrust proposes efficient and randomized algorithmsto address arbitrary outliers.
大规模数据采集技术的迅速发展,促使人们对高维机器学习进行研究. 例如,设计推荐系统的问题,如亚马逊,Netflix和其他在线公司所使用的,涉及分析描述用户在过去情况下行为的大型矩阵。 在社会学中,研究人员对将网络与大规模数据集相匹配感兴趣,这些数据集涉及数百或数千个个体。 在医学成像中,目标是重建复杂的现象(例如,大脑图像;跳动的心脏的视频)基于最少数量的不完整和可能损坏的测量。 基于这些应用背景,本研究的目标是利用凸优化、信号处理和鲁棒统计等工具,以健壮和可扩展的方式开发和分析从高维数据集中提取相关结构的模型和算法. 它包括三个主要的推力:(1)模型的限制性:成功的方法为high-dimensionaldata利用低维结构,然而,许多现实世界的问题落在现有模型的范围之外。 这一提议通过允许多个结构显著扩展了基本设置,从而导致计算效率高的算法,同时消除了模型不匹配的负面影响。 (2)非理想数据:缺失数据在现实问题中很普遍,并且可能导致高维数据标准算法的重大故障。第二个推力设计松弛和贪婪的方法对thesen-convex问题。 (3)任意离群值:由于各种原因,包括易于出错的传感器和操纵剂,可能会出现严重错误。 第三个推力提出了有效的和随机的算法来解决任意离群值。
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
- DOI:
- 发表时间:
2007 - 期刊:
- 影响因子:0
- 作者:
Sujay Sanghavi;V. Tan;A. Willsky - 通讯作者:
A. Willsky
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:
$ 69.54万 - 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:
$ 69.54万 - 项目类别:
Continuing Grant
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
- 批准号:
1564000 - 财政年份:2016
- 资助金额:
$ 69.54万 - 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:
$ 69.54万 - 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:
$ 69.54万 - 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:
$ 69.54万 - 项目类别:
Continuing Grant
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:
$ 69.54万 - 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:
$ 69.54万 - 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:
$ 69.54万 - 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:
$ 69.54万 - 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:
$ 69.54万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Medium: Fundamental Limits of Cache-aided Multi-user Private Function Retrieval
协作研究:CIF:中:缓存辅助多用户私有函数检索的基本限制
- 批准号:
2312229 - 财政年份:2023
- 资助金额:
$ 69.54万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Statistical and Algorithmic Foundations of Distributionally Robust Policy Learning
合作研究:CIF:媒介:分布式稳健政策学习的统计和算法基础
- 批准号:
2312205 - 财政年份:2023
- 资助金额:
$ 69.54万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Fundamental Limits of Privacy-Enhancing Technologies
合作研究:CIF:中:隐私增强技术的基本限制
- 批准号:
2312666 - 财政年份:2023
- 资助金额:
$ 69.54万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Fundamental Limits of Cache-aided Multi-user Private Function Retrieval
协作研究:CIF:中:缓存辅助多用户私有函数检索的基本限制
- 批准号:
2312228 - 财政年份:2023
- 资助金额:
$ 69.54万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Robust Learning over Graphs
协作研究:CIF:媒介:图上的鲁棒学习
- 批准号:
2312547 - 财政年份:2023
- 资助金额:
$ 69.54万 - 项目类别:
Continuing Grant