Collaborative Research: Connecting Submodularity and Restricted Strong Convexity

合作研究:连接子模性和受限强凸性

基本信息

  • 批准号:
    1723052
  • 负责人:
  • 金额:
    $ 9万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2017
  • 资助国家:
    美国
  • 起止时间:
    2017-09-01 至 2020-08-31
  • 项目状态:
    已结题

项目摘要

Structured estimation problems arise in a variety of contexts including astronomy, genomics, and computer vision. This project aims to develop methods that can use the additional structure in order to estimate statistical models effectively, while also using the structure for computational improvements. This work seeks to connect ideas in combinatorial optimization and statistical estimation to develop computationally tractable methods for performing structured statistical estimation.This project provides an integrated program to explore and connect combinatorial optimization and statistical estimation. Modern statistical challenges have become increasingly dependent on understanding both the computational and statistical issues. Many modern statistical estimation problems rely on imposing additional structure in order to reduce the statistical complexity and provide interpretability. Unfortunately, these structures often are combinatorial in nature and result in computationally challenging problems. In parallel, the combinatorial optimization community has placed significant effort in developing algorithms that can approximately solve such optimization problems in a computationally efficient manner. The focus of this project is to expand upon ideas that arise in combinatorial optimization and connect those algorithms and ideas to statistical questions. The research directions of this project are split into three main thrusts unified by the concept of weak submodularity: (a) cardinality constrained optimization and its applications to general statistical optimization problems; (b) matrix estimation problems including low-rank matrix estimation and semi-definite programming problems as well as problems in sparse dictionary learning; and (c) a general theoretical understanding of weak submodularity and specifically analyzing how to develop algorithms in this regime that work well for large-scale datasets.
结构化估计问题出现在各种背景下,包括天文学,基因组学和计算机视觉。该项目旨在开发可以使用附加结构的方法,以便有效地估计统计模型,同时还使用该结构进行计算改进。本项目旨在将组合优化和统计估计的思想结合起来,以开发计算上易于处理的方法来执行结构化统计估计。本项目提供了一个综合程序来探索和连接组合优化和统计估计。现代统计学的挑战越来越依赖于对计算和统计问题的理解。许多现代统计估计问题依赖于施加额外的结构,以减少统计的复杂性,并提供可解释性。不幸的是,这些结构通常是组合的性质,并导致计算上具有挑战性的问题。并行地,组合优化社区已经在开发能够以计算高效的方式近似地解决这样的优化问题的算法方面投入了大量的努力。这个项目的重点是扩展组合优化中出现的想法,并将这些算法和想法与统计问题联系起来。该项目的研究方向被划分为三个主要方向:(a)基数约束优化及其在一般统计优化问题中的应用,(B)矩阵估计问题,包括低秩矩阵估计和半定规划问题,以及稀疏字典学习问题,(b)矩阵估计问题,包括半定规划问题和稀疏字典学习问题。以及(c)对弱子模块性的一般理论理解,并具体分析如何在此机制下开发适用于大规模数据集的算法。

项目成果

期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
  • DOI:
  • 发表时间:
    2017-03
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ethan R. Elenberg;A. Dimakis;Moran Feldman;Amin Karbasi
  • 通讯作者:
    Ethan R. Elenberg;A. Dimakis;Moran Feldman;Amin Karbasi
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
  • DOI:
  • 发表时间:
    2018-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Qi Lei;Lingfei Wu;Pin-Yu Chen;A. Dimakis;I. Dhillon;M. Witbrock
  • 通讯作者:
    Qi Lei;Lingfei Wu;Pin-Yu Chen;A. Dimakis;I. Dhillon;M. Witbrock
Restricted Strong Convexity Implies Weak Submodularity
  • DOI:
    10.1214/17-aos1679
  • 发表时间:
    2016-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ethan R. Elenberg;Rajiv Khanna;A. Dimakis;S. Negahban
  • 通讯作者:
    Ethan R. Elenberg;Rajiv Khanna;A. Dimakis;S. Negahban
{{ 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 }}

Georgios-Alex Dimakis其他文献

Georgios-Alex Dimakis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('Georgios-Alex Dimakis', 18)}}的其他基金

AF: Medium: Collaborative Research: Theoretical Foundations of Deep Generative Models and High-Dimensional Distributions
AF:中:协作研究:深度生成模型和高维分布的理论基础
  • 批准号:
    1901281
  • 财政年份:
    2019
  • 资助金额:
    $ 9万
  • 项目类别:
    Continuing Grant
CIF: Medium: Collaborative Research: Coded Computing for Large-Scale Machine Learning
CIF:媒介:协作研究:大规模机器学习的编码计算
  • 批准号:
    1763702
  • 财政年份:
    2018
  • 资助金额:
    $ 9万
  • 项目类别:
    Continuing Grant
CIF: Small: Index Coding and Matrix Factorizations
CIF:小:索引编码和矩阵分解
  • 批准号:
    1618689
  • 财政年份:
    2016
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
CIF: Medium: Collaborative Research: Content Delivery over Heterogeneous Networks: Fundamental Limits and Distributed Algorithms
CIF:媒介:协作研究:异构网络上的内容交付:基本限制和分布式算法
  • 批准号:
    1407278
  • 财政年份:
    2014
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
CIF: Small: Sparsity in Quadratic Optimization through Low-Rank Approximations
CIF:小:通过低阶近似实现二次优化的稀疏性
  • 批准号:
    1422549
  • 财政年份:
    2014
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
CAREER: Network Coding Theory for Distributed Storage
职业:分布式存储的网络编码理论
  • 批准号:
    1344179
  • 财政年份:
    2013
  • 资助金额:
    $ 9万
  • 项目类别:
    Continuing Grant
CIF: Small: Collaborative Research: Design and Analysis of Novel Compressed Sensing Algorithms via Connections with Coding Theory
CIF:小型:协作研究:通过与编码理论的联系设计和分析新型压缩感知算法
  • 批准号:
    1344364
  • 财政年份:
    2013
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
CIF: Small: Collaborative Research: Design and Analysis of Novel Compressed Sensing Algorithms via Connections with Coding Theory
CIF:小型:协作研究:通过与编码理论的联系设计和分析新型压缩感知算法
  • 批准号:
    1218235
  • 财政年份:
    2012
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
CAREER: Network Coding Theory for Distributed Storage
职业:分布式存储的网络编码理论
  • 批准号:
    1055099
  • 财政年份:
    2011
  • 资助金额:
    $ 9万
  • 项目类别:
    Continuing 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: Connecting the Past, Present, and Future Climate of the Lake Victoria Basin using High-Resolution Coupled Modeling
合作研究:使用高分辨率耦合建模连接维多利亚湖盆地的过去、现在和未来气候
  • 批准号:
    2323649
  • 财政年份:
    2024
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Connecting the Past, Present, and Future Climate of the Lake Victoria Basin using High-Resolution Coupled Modeling
合作研究:使用高分辨率耦合建模连接维多利亚湖盆地的过去、现在和未来气候
  • 批准号:
    2323648
  • 财政年份:
    2024
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Disciplinary Improvements for Past Global Change Research: Connecting Data Systems and Practitioners
协作研究:过去全球变化研究的学科改进:连接数据系统和从业者
  • 批准号:
    2347014
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Disciplinary Improvements for Past Global Change Research: Connecting Data Systems and Practitioners
协作研究:过去全球变化研究的学科改进:连接数据系统和从业者
  • 批准号:
    2226372
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Connecting the sequence logic of RNA splicing to nuclear localization
合作研究:将 RNA 剪接的序列逻辑与核定位联系起来
  • 批准号:
    2246530
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Connecting the sequence logic of RNA splicing to nuclear localization
合作研究:将 RNA 剪接的序列逻辑与核定位联系起来
  • 批准号:
    2246531
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Disciplinary Improvements for Past Global Change Research: Connecting Data Systems and Practitioners
协作研究:过去全球变化研究的学科改进:连接数据系统和从业者
  • 批准号:
    2226371
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Conference: Supporting inclusive and sustainable research infrastructure for systematics (SISRIS) by connecting scientists and their specimens.
协作研究:会议:通过连接科学家及其标本,支持包容性和可持续的系统学研究基础设施 (SISRIS)。
  • 批准号:
    2247631
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: HCC: Medium: Connecting Practitioners to Design: Methods and Tools for Live Participatory Design Fiction
合作研究:HCC:媒介:将从业者与设计联系起来:现场参与式设计小说的方法和工具
  • 批准号:
    2425383
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
Collaborative Research: Disciplinary Improvements for Past Global Change Research: Connecting Data Systems and Practitioners
协作研究:过去全球变化研究的学科改进:连接数据系统和从业者
  • 批准号:
    2226369
  • 财政年份:
    2023
  • 资助金额:
    $ 9万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了