CAREER: Embracing Local Minima and Nonsmoothness in Nonconvex Statistical Estimation: From Structures to Algorithms

职业:在非凸统计估计中拥抱局部极小值和非平滑性:从结构到算法

基本信息

  • 批准号:
    2233152
  • 负责人:
  • 金额:
    $ 54.28万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-10-01 至 2026-02-28
  • 项目状态:
    未结题

项目摘要

Optimization plays a crucial role in modern data analysis. Accurate modeling and robust analysis of complex datasets often require solving a class of optimization problems that are not smooth and may possess many low-quality solutions. These problems are challenging to solve, and there is limited understanding of the properties of solutions returned by standard algorithms. Existing approaches typically steer away from such problems or restrict to a small subset of them. This project aims to substantially broaden the class of problems for which efficient algorithms exist, and for which performance guarantees can be obtained. The project will develop new algorithms and analytical tools that are applicable in a broad range of engineering and science applications. Furthermore, the project will support an education plan that centers around the goal of bridging the disciplines of optimization and statistics at both undergraduate and graduate levels.The technical approaches of this project are based on the general principles of decoupling nonsmoothness and nonconvexity, and identifying the characteristic structures of locally optimal solutions. The research program consists of two main thrusts: (1) study a class of nonsmooth composite optimization problems and develop a framework for quantifying the average-case conditioning of the problems and the convergence rates of low-complexity algorithms; (2) consider a class of problems with coupled components, characterize the hidden structures of the local minima, and exploit these structural results to design and analyze efficient algorithms in settings where existing results fail to apply. The research in this project will cover a diverse set of important statistical and machine learning problems. The techniques developed will provide a refined analysis of the algorithmic performance for average-case problems in statistical settings.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.
优化在现代数据分析中起着至关重要的作用。复杂数据集的精确建模和鲁棒分析通常需要解决一类不光滑的优化问题,并且可能具有许多低质量的解。这些问题很难解决,而且人们对标准算法返回的解的性质了解有限。现有的方法通常会避开这些问题,或者只局限于其中的一小部分。该项目旨在实质性地扩大问题的类别,这些问题存在有效的算法,并且可以获得性能保证。该项目将开发适用于广泛工程和科学应用的新算法和分析工具。此外,该项目将支持一项教育计划,该计划的中心目标是在本科和研究生阶段架起优化和统计学学科的桥梁。本课题的技术方法是基于非光滑性和非凸性解耦的一般原理,识别局部最优解的特征结构。本研究主要包括两个方面的内容:(1)研究一类非光滑复合优化问题,并建立一个框架来量化问题的平均情况条件和低复杂度算法的收敛速度;(2)考虑一类具有耦合分量的问题,表征局部最小值的隐藏结构,并利用这些结构结果来设计和分析在现有结果不适用的情况下的有效算法。该项目的研究将涵盖一系列重要的统计和机器学习问题。所开发的技术将为统计设置中的平均情况问题的算法性能提供精细分析。该奖项反映了美国国家科学基金会的法定使命,并通过使用基金会的知识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(12)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
Low-Rank Matrix Recovery with Composite Optimization: Good Conditioning and Rapid Convergence
  • DOI:
    10.1007/s10208-020-09490-9
  • 发表时间:
    2021-01-28
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Charisopoulos, Vasileios;Chen, Yudong;Drusvyatskiy, Dmitriy
  • 通讯作者:
    Drusvyatskiy, Dmitriy
Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium
  • DOI:
  • 发表时间:
    2020-02
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Qiaomin Xie;Yudong Chen;Zhaoran Wang;Zhuoran Yang
  • 通讯作者:
    Qiaomin Xie;Yudong Chen;Zhaoran Wang;Zhuoran Yang
Clustering heterogeneous financial networks
集群异构金融网络
  • DOI:
    10.1111/mafi.12407
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    1.6
  • 作者:
    Amini, Hamed;Chen, Yudong;Minca, Andreea;Qian, Xin
  • 通讯作者:
    Qian, Xin
Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
{{ 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 }}

Yudong Chen其他文献

Evaluation of Mercury Uptake and Distribution in Rice (Oryza sativa L.)
水稻 (Oryza sativa L.) 汞吸收和分布的评价
Tailoring spin angular momentum: Design principles for plasmonic nanostructures
定制自旋角动量:等离子体纳米结构的设计原理
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    4.6
  • 作者:
    Wen Xiao;Yudong Chen;Kui Han;Xiaopeng Shen;Weihua Wang
  • 通讯作者:
    Weihua Wang
Clustering Without an Eigengap
无特征间隙的聚类
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    M. Zurek;Yudong Chen
  • 通讯作者:
    Yudong Chen
Local Minima Structures in Gaussian Mixture Models
高斯混合模型中的局部极小结构
  • DOI:
    10.1109/tit.2024.3374716
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    2.5
  • 作者:
    Yudong Chen;Dogyoon Song;Xumei Xi;Yuqian Zhang
  • 通讯作者:
    Yuqian Zhang
Sandwich-like PPy/NiCo-LDH heterostructure for high-performance flexible supercapacitors
用于高性能柔性超级电容器的类三明治结构的聚吡咯/镍钴 - 层状双氢氧化物异质结构
  • DOI:
    10.1016/j.apsusc.2025.162641
  • 发表时间:
    2025-05-01
  • 期刊:
  • 影响因子:
    6.900
  • 作者:
    Leilin Zhuo;Huangqing Zhang;Qingwei Huang;Yudong Chen;Xiaohong Liu;Qian Cai;Wengong Zhang;Hong Chen;Zhenghuan Lin;Qidan Ling
  • 通讯作者:
    Qidan Ling

Yudong Chen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('Yudong Chen', 18)}}的其他基金

CAREER: Embracing Local Minima and Nonsmoothness in Nonconvex Statistical Estimation: From Structures to Algorithms
职业:在非凸统计估计中拥抱局部极小值和非平滑性:从结构到算法
  • 批准号:
    2047910
  • 财政年份:
    2021
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Continuing Grant
CRII: CIF: Limits and Robustness of Nonconvex Low-Rank Estimation
CRII:CIF:非凸低秩估计的局限性和鲁棒性
  • 批准号:
    1657420
  • 财政年份:
    2017
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Standard Grant
CIF: Medium: Collaborative Research: Nonconvex Optimization for High-Dimensional Signal Estimation: Theory and Fast Algorithms
CIF:中:协作研究:高维信号估计的非凸优化:理论和快速算法
  • 批准号:
    1704828
  • 财政年份:
    2017
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Continuing Grant

相似海外基金

REU Site: Embracing Blockchain for a Secure and Trustworthy Tomorrow
REU 网站:拥抱区块链,打造安全可信的明天
  • 批准号:
    2349042
  • 财政年份:
    2024
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Standard Grant
Embracing Changes for Responsive Video-sharing Services
拥抱响应式视频共享服务的变革
  • 批准号:
    DP240101814
  • 财政年份:
    2024
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Discovery Projects
Embracing diversity: a multi-phased project to advance the science of knowledge mobilization for Canada's culturally diverse groups
拥抱多样性:一个多阶段项目,旨在推动加拿大文化多元化群体的知识动员科学
  • 批准号:
    489584
  • 财政年份:
    2023
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Operating Grants
Radical hope beyond hospitality and tolerance: embracing pro-migrant futures out of the UK's hostile environment
超越好客和宽容的激进希望:拥抱支持移民的未来,摆脱英国的敌对环境
  • 批准号:
    2863889
  • 财政年份:
    2023
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Studentship
Embracing complexity in the characterisation and trcking of individual wellbeing across development
拥抱发展过程中个人福祉特征和跟踪的复杂性
  • 批准号:
    2711931
  • 财政年份:
    2022
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Studentship
EMBRACing changE: Overcoming obstacles and advancing democracy in the European Neighbourhood
拥抱变革:克服欧洲邻国的障碍并推进民主
  • 批准号:
    10040966
  • 财政年份:
    2022
  • 资助金额:
    $ 54.28万
  • 项目类别:
    EU-Funded
Canadian Association of Psychosocial Oncology (CAPO) and International Psychosocial Oncology Society (IPOS) 2022 World Conference. Reimagining psychosocial oncology; Embracing voices from around the world.
加拿大心理社会肿瘤学协会 (CAPO) 和国际心理社会肿瘤学协会 (IPOS) 2022 年世界会议。
  • 批准号:
    460770
  • 财政年份:
    2022
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Miscellaneous Programs
BMES 2022 Annual Meeting “Embracing Inclusion to Advance Innovation in Healthcare and Education”; San Antonio, Texas; 12-15 October 2022.
BMES 2022年年会“拥抱包容性,推进医疗保健和教育创新”;
  • 批准号:
    2236724
  • 财政年份:
    2022
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Standard Grant
Overcoming and embracing oxidation for the synthesis of bioactive molecules
克服并拥抱氧化以合成生物活性分子
  • 批准号:
    576253-2022
  • 财政年份:
    2022
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Alliance Grants
Embracing gauge-freedom in ultrastrong-coupling quantum electrodynamics
在超强耦合量子电动力学中拥抱规范自由
  • 批准号:
    EP/V048562/1
  • 财政年份:
    2021
  • 资助金额:
    $ 54.28万
  • 项目类别:
    Research Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了