权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Elements: Software: NSCI: A high performance suite of SVD related solvers for machine learning

要素：软件：NSCI：用于机器学习的 SVD 相关求解器的高性能套件

基本信息

批准号：
1835821
负责人：
Andreas Stathopoulos
金额：
$ 60万
依托单位：
College of William and Mary
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-01-01 至 2023-12-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1835821&HistoricalAwards=false
关键词：
Elements Software NSCI performance suite

项目摘要

The accrual of vast amounts of data is one of the defining characteristics of our century. With the help of computers, scientists use this data to make and test hypotheses, draw inferences, predict complex phenomena, and make educated policy decisions. Machine learning (ML) is an area in computer science that uses statistical methods to allow computers to "learn" from data, with and without human supervision. Central to the application of machine learning methods is the numerical computation of the Singular Value Decomposition (SVD) of matrices of very large dimension, often larger than a million or even a billion. Since "off-the-shelf" algorithms and SVD software, however, cannot handle matrices of very large dimension, iterative methods used in scientific computing are more appropriate. Yet their stringent approximation quality requirements are often excessive for downstream applications, and result in slow execution times. Recently, methods based on randomization have improved execution times, but their implementations relax the approximation quality, often to detrimental levels. This project proposes to develop a software package that unifies randomized and iterative methods with a particular focus on the specific requirements of various ML applications and with high performance optimizations for modern computing platforms. This will allow scientists to analyze significantly larger datasets, ML researchers to study large models that could not be tackled before, and ML service providers to use the new solvers to reduce their operational cost. This project proposes to develop a software package that unifies randomized and iterative methods with a particular focus on the specific requirements of various ML applications and with high performance optimizations for modern computing platforms. This will allow scientists to analyze significantly larger datasets, ML researchers to study large models that could not be tackled before, and ML service providers to use the new solvers to reduce their operational cost. Specifically, the software package builds upon the state-of-the-art eigenvalue/singular value software package PRIMME that integrates cutting-edge iterative methods and high-performance implementations. The development of the package consists of two thrusts: (T1) Unifying state-of-the-art algorithmic techniques including randomized, streaming, and iterative methods, to deliver consistent experience for a diverse range of matrices with different quality requirements, hardware platforms and precisions, and programming environments. (T2) Developing software devices that enable downstream systems and SVD solvers to interoperate so that users can tune and customize solvers without being experts in numeric linear algebra.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.

海量数据的积累是我们这个世纪的决定性特征之一。在计算机的帮助下，科学家使用这些数据来做出和检验假设，得出推论，预测复杂的现象，并做出明智的政策决定。机器学习(ML)是计算机科学中的一个领域，它使用统计学方法允许计算机在有人监督和没有人监督的情况下从数据中“学习”。机器学习方法应用的中心是对非常大的维矩阵的奇异值分解(SVD)的数值计算，这些矩阵通常大于一百万甚至十亿。然而，由于“现成”算法和奇异值分解软件不能处理非常大的维矩阵，因此在科学计算中使用迭代方法更为合适。然而，它们严格的近似质量要求对于下游应用程序来说往往是过高的，并导致执行时间较慢。最近，基于随机化的方法改善了执行时间，但它们的实现放松了近似质量，往往达到有害的水平。该项目建议开发一个软件包，将随机化和迭代方法统一起来，特别关注各种ML应用的特定要求，并针对现代计算平台进行高性能优化。这将使科学家能够分析更大的数据集，ML研究人员可以研究以前无法解决的大型模型，ML服务提供商可以使用新的解算器来降低他们的运营成本。该项目建议开发一个软件包，将随机化和迭代方法统一起来，特别关注各种ML应用的特定要求，并针对现代计算平台进行高性能优化。这将使科学家能够分析更大的数据集，ML研究人员可以研究以前无法解决的大型模型，ML服务提供商可以使用新的解算器来降低他们的运营成本。具体地说，该软件包建立在最先进的特征值/奇异值软件包PRIMME的基础上，该软件包集成了尖端迭代方法和高性能实现。该包的开发包括两个方面：(1)统一包括随机化、流和迭代方法在内的最先进的算法技术，为具有不同质量要求、硬件平台和精度以及编程环境的各种矩阵提供一致的体验。(T2)开发软件设备，使下游系统和奇异值分解求解器能够互操作，以便用户无需成为数值线性代数专家即可调整和定制求解器。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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（11）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

A Deep Learning Framework for Pricing Financial Instruments

DOI：
发表时间：
2019-09
期刊：
ArXiv
影响因子：
0
作者：
Qiong Wu;Zheng Zhang;A. Pizzoferrato;Mihai Cucuringu;Zhenming Liu
通讯作者：
Qiong Wu;Zheng Zhang;A. Pizzoferrato;Mihai Cucuringu;Zhenming Liu

BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation

DOI：
10.1145/3468268
发表时间：
2021-12-01
期刊：
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
影响因子：
5
作者：
Wu, Qiong;Hare, Adam;Li, Yanhua
通讯作者：
Li, Yanhua

Equity2Vec: end-to-end deep learning framework for cross-sectional asset pricing

DOI：
10.1145/3490354.3494409
发表时间：
2019-09
期刊：
Proceedings of the Second ACM International Conference on AI in Finance
影响因子：
0
作者：
Qiong Wu;Christopher G. Brinton;Zhenghao Zhang;A. Pizzoferrato;Zhenming Liu;Mihai Cucuringu
通讯作者：
Qiong Wu;Christopher G. Brinton;Zhenghao Zhang;A. Pizzoferrato;Zhenming Liu;Mihai Cucuringu

Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models