III: Small: Effective Convex Solvers for Machine Learning
III: Small: Effective Convex Solvers for Machine Learning
批准号:
1319749
负责人:
Daniel Boley
金额:
$43.75万
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
项目状态:
已结题
起止时间:
2013-09-01 至 2018-08-31
中文摘要
点击翻译按钮获取中文摘要
英文摘要
Many large scale machine learning problems are formulated as optimization problems, in which some measure of error or loss is to be minimized over a suitable training corpus. Real problems have too many data points to fit in a single computer. Hence the data and/or computation must be distributed over a network of computers. Often the only practical methods for extremely large problems are so-called splitting methods, but their convergence properties are extremely variable: sometimes very fast, sometimes very slow, in ways that can be hard to predict. The goal of this project is to gain a better understanding of the convergence behavior and to use this understanding to construct accelerated algorithms with more consistent convergence properties. This will allow the application of machine learning techniques to a much wider class of problems.Splitting methods (or more precisely alternating direction methods) are based on the idea that a general convex optimization problem can be split into two or more parts, each of which can be solved much more easily compared to the problem as a whole. The methods cycle through all the variables in turn, optimizing over each subset of variables leaving the rest fixed. The proposed work builds on a preliminary analysis of a simple model problem using the eigen-structure of certain matrix operators. The project is devoted to extending this analysis to more general problems, as well as developing faster solvers using well-established computational technologies for the matrix eigenvalue problem. Success will be measured in terms of the generality of the theory developed and the improvements in the observed convergence behavior on real problems.With faster solvers, discovery of major regions of influence in a global-scale social network (e.g. Facebook or Twitter) could become practical on modest computer platforms. The same holds for tracking disease propagation and people in video sequences. With efficient solvers, tracking software could be deployed on local hardware without the need for high-powered central servers. This will lead to advances in countless areas such data mining, compressive sensing, recommender systems, signal processing, missing data imputation, analysis of large scale social, biological or computer networks, image reconstruction, denoising and classification.The results of this research are to be disseminated in papers in the principal journals and conferences in machine learning, data mining, and optimization as well as in the form of software packages via the WWW (http://www-users.cs.umn.edu/~boley/ML-Optimization).The project depends on the interaction between different disciplines and applications areas, which will attract students from a variety of backgrounds at both the graduate and undergraduate level. Some research tasks are suitable as projects in classes on linear algebra, optimization, data mining, machine learning and are to be developed for both undergraduate and graduate students. Undergraduate students, including women and members of underrepresented groups, will see the value of mathematical algorithms to solve real problems of interest to them.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
REU Site: Computational Methods for Discovery Driven by Big Data
-
批准号:1460620
-
项目类别:Standard Grant
-
资助金额:$36.0万
-
财政年份:2015
-
负责人:Daniel Boley
-
依托单位:
Effective Learning by Leveraging Supervised and Unsupervised Techniques
-
批准号:0534286
-
项目类别:Continuing Grant
-
资助金额:$0.0万
-
财政年份:2005
-
负责人:Daniel Boley
-
依托单位:
General Purpose Methods for Unsupervised Exploration of Large Datasets
-
批准号:0208621
-
项目类别:Continuing Grant
-
资助金额:$15.0万
-
财政年份:2002
-
负责人:Daniel Boley
-
依托单位:
Unsupervised Document Set Exploration Using Divisive Partitioning
-
批准号:9811229
-
项目类别:Continuing Grant
-
资助金额:$18.0万
-
财政年份:1998
-
负责人:Daniel Boley
-
依托单位:
Robust Fault Tolerance for Computations in Linear Algebra and Signal Processing
-
批准号:9628786
-
项目类别:Standard Grant
-
资助金额:$5.99万
-
财政年份:1996
-
负责人:Daniel Boley
-
依托单位:
Numerical Methods for Very Large Sparse Dynamical Systems
-
批准号:9405380
-
项目类别:Standard Grant
-
资助金额:$18.0万
-
财政年份:1994
-
负责人:Daniel Boley
-
依托单位:
A Study of Large Matrix Eigenvalue Problems
-
批准号:8813493
-
项目类别:Continuing Grant
-
资助金额:$15.88万
-
财政年份:1988
-
负责人:Daniel Boley
-
依托单位:
Large Matrix Eigenvalue and Singular Value Problems
-
批准号:8519029
-
项目类别:Standard Grant
-
资助金额:$6.9万
-
财政年份:1986
-
负责人:Daniel Boley
-
依托单位:
Research Initiation: Numerical Problems in Linear Control Theory
-
批准号:8204468
-
项目类别:Standard Grant
-
资助金额:$4.33万
-
财政年份:1982
-
负责人:Daniel Boley
-
依托单位:
国内基金
海外基金
登录
查看更多内容
昼夜节律性small RNA在血斑形成时间推断中的法医学应用研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2024
-
负责人:
-
依托单位:
tRNA-derived small RNA上调YBX1/CCL5通路参与硼替佐米诱导慢性疼痛的机制研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:10.0万元
-
批准年份:2022
-
负责人:张祥忠
-
依托单位:
Small RNA调控I-F型CRISPR-Cas适应性免疫性的应答及分子机制
-
批准号:32000033
-
项目类别:青年科学基金项目
-
资助金额:24.0万元
-
批准年份:2020
-
负责人:林平
-
依托单位:
Small RNAs调控解淀粉芽胞杆菌FZB42生防功能的机制研究
-
批准号:31972324
-
项目类别:面上项目
-
资助金额:58.0万元
-
批准年份:2019
-
负责人:高学文
-
依托单位:
变异链球菌small RNAs连接LuxS密度感应与生物膜形成的机制研究
-
批准号:81900988
-
项目类别:青年科学基金项目
-
资助金额:21.0万元
-
批准年份:2019
-
负责人:毛梦莹
-
依托单位:
肠道细菌关键small RNAs在克罗恩病发生发展中的功能和作用机制
-
批准号:31870821
-
项目类别:面上项目
-
资助金额:56.0万元
-
批准年份:2018
-
负责人:陈江宁
-
依托单位:
基于small RNA 测序技术解析鸽分泌鸽乳的分子机制
-
批准号:31802058
-
项目类别:青年科学基金项目
-
资助金额:26.0万元
-
批准年份:2018
-
负责人:麻慧
-
依托单位:
Small RNA介导的DNA甲基化调控的水稻草矮病毒致病机制
-
批准号:31772128
-
项目类别:面上项目
-
资助金额:60.0万元
-
批准年份:2017
-
负责人:吴建国
-
依托单位:
基于small RNA-seq的针灸治疗桥本甲状腺炎的免疫调控机制研究
-
批准号:81704176
-
项目类别:青年科学基金项目
-
资助金额:20.0万元
-
批准年份:2017
-
负责人:赵继梦
-
依托单位:
水稻OsSGS3与OsHEN1调控small RNAs合成及其对抗病性的调节
-
批准号:91640114
-
项目类别:重大研究计划
-
资助金额:85.0万元
-
批准年份:2016
-
负责人:何祖华
-
依托单位: