BIGDATA: Collaborative Research: F: Stochastic Approximation for Subspace and Multiview Representation Learning
BIGDATA:协作研究:F:子空间和多视图表示学习的随机逼近
基本信息
- 批准号:1546500
- 负责人:
- 金额:$ 39.45万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2015
- 资助国家:美国
- 起止时间:2015-09-01 至 2021-08-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Unsupervised learning of useful features, or representations, is one of the most basic challenges of machine learning. Unsupervised representation learning techniques capitalize on unlabeled data which is often cheap and abundant and sometimes virtually unlimited. The goal of these ubiquitous techniques is to learn a representation that reveals intrinsic low-dimensional structure in data, disentangles underlying factors of variation by incorporating universal AI priors such as smoothness and sparsity, and is useful across multiple tasks and domains. This project aims to develop new theory and methods for representation learning that can easily scale to large datasets. In particular, this project is concerned with methods for large-scale unsupervised feature learning, including Principal Component Analysis (PCA) and Partial Least Squares (PLS). To capitalize on massive amounts of unlabeled data, this project will develop appropriate computational approaches and study them in the ?data laden? regime. Therefore, instead of viewing representation learning as dimensionality reduction techniques and focusing on an empirical objective on finite data, these methods are studied with the goal of optimizing a population objective based on sample. This view suggests using Stochastic Approximation approaches, such as Stochastic Gradient Descent (SGD) and Stochastic Mirror Descent, that are incremental in nature and process each new sample with a computationally cheap update. Furthermore, this view enables a rigorous analysis of benefits of stochastic approximation algorithms over traditional finite-data methods. The project aims to develop stochastic approximation approaches to PCA and PLS and related problems and extensions, including deep, and sparse variants, and analyze these problems in the data-laden regime.
有用特征或表示的无监督学习是机器学习最基本的挑战之一。无监督表示学习技术利用未标记的数据,这些数据通常是廉价和丰富的,有时几乎是无限的。这些无处不在的技术的目标是学习一种表示,揭示数据中的内在低维结构,通过结合通用AI先验(如平滑性和稀疏性)来解开潜在的变化因素,并在多个任务和领域中有用。该项目旨在开发新的理论和方法,用于表示学习,可以轻松扩展到大型数据集。特别是,该项目涉及大规模无监督特征学习的方法,包括主成分分析(PCA)和偏最小二乘(PLS)。为了利用大量的未标记的数据,该项目将开发适当的计算方法,并在?数据负载?政权因此,这些方法不是将表示学习视为降维技术并专注于有限数据上的经验目标,而是以基于样本优化群体目标为目标进行研究。这种观点建议使用随机近似方法,如随机梯度下降(SGD)和随机镜像下降,这些方法本质上是增量的,并且使用计算成本较低的更新来处理每个新样本。此外,这一观点使得严格的分析的好处随机逼近算法在传统的有限数据方法。该项目旨在开发PCA和PLS的随机近似方法以及相关问题和扩展,包括深度和稀疏变量,并在数据负载制度中分析这些问题。
项目成果
期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Efficiently Learning Adversarially Robust Halfspaces with Noise
- DOI:
- 发表时间:2020-05
- 期刊:
- 影响因子:0
- 作者:Omar Montasser;Surbhi Goel;Ilias Diakonikolas;N. Srebro
- 通讯作者:Omar Montasser;Surbhi Goel;Ilias Diakonikolas;N. Srebro
The Everlasting Database: Statistical Validity at a Fair Price
- DOI:
- 发表时间:2018-03
- 期刊:
- 影响因子:0
- 作者:Blake E. Woodworth;V. Feldman;Saharon Rosset;N. Srebro
- 通讯作者:Blake E. Woodworth;V. Feldman;Saharon Rosset;N. Srebro
Efficient coordinate-wise leading eigenvector computation
- DOI:
- 发表时间:2017-02
- 期刊:
- 影响因子:0
- 作者:Jialei Wang;Weiran Wang;D. Garber;N. Srebro
- 通讯作者:Jialei Wang;Weiran Wang;D. Garber;N. Srebro
Reducing Adversarially Robust Learning to Non-Robust PAC Learning
- DOI:
- 发表时间:2020-10
- 期刊:
- 影响因子:0
- 作者:Omar Montasser;Steve Hanneke;N. Srebro
- 通讯作者:Omar Montasser;Steve Hanneke;N. Srebro
Does invariant risk minimization capture invariance?
不变风险最小化是否捕获了不变性?
- DOI:
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Kamath Pritish, Tangella Akilesh
- 通讯作者:Kamath Pritish, Tangella Akilesh
{{
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 }}
Nathan Srebro其他文献
Score Design for Multi-Criteria Incentivization
多标准激励的评分设计
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Anmol Kabra;Mina Karzand;Tosca Lechner;Nathan Srebro;Serena Lutong Wang - 通讯作者:
Serena Lutong Wang
Fixed-structure H∞ controller design based on Distributed Probabilistic Model-Building Genetic Algorithm
基于分布式概率建模遗传算法的固定结构H∞控制器设计
- DOI:
10.2316/p.2011.744-072 - 发表时间:
2011 - 期刊:
- 影响因子:0
- 作者:
Michihiro Kawanishi;Tomohiro Kaneko;Tatsuo Narikiyo;Nathan Srebro - 通讯作者:
Nathan Srebro
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
关于通过统计和梯度查询学习稀疏函数的复杂性
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Nirmit Joshi;Theodor Misiakiewicz;Nathan Srebro - 通讯作者:
Nathan Srebro
Nathan Srebro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('Nathan Srebro', 18)}}的其他基金
HDR TRIPODS: Collaborative Research: Institute for Data, Econometrics, Algorithms and Learning
HDR TRIPODS:协作研究:数据、计量经济学、算法和学习研究所
- 批准号:
1934843 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Continuing Grant
AF: RI: Medium: Collaborative Research: Understanding and Improving Optimization in Deep and Recurrent Networks
AF:RI:中:协作研究:理解和改进深度和循环网络的优化
- 批准号:
1764032 - 财政年份:2018
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
CCF-BSF: AF: Small: Convex and Non-Convex Distributed Learning
CCF-BSF:AF:小:凸和非凸分布式学习
- 批准号:
1718970 - 财政年份:2018
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
RI: AF: Medium: Learning and Matrix Reconstruction with the Max-Norm and Related Factorization Norms
RI:AF:中:使用最大范数和相关因式分解范数进行学习和矩阵重建
- 批准号:
1302662 - 财政年份:2013
- 资助金额:
$ 39.45万 - 项目类别:
Continuing Grant
相似海外基金
BIGDATA: IA: Collaborative Research: Asynchronous Distributed Machine Learning Framework for Multi-Site Collaborative Brain Big Data Mining
BIGDATA:IA:协作研究:用于多站点协作大脑大数据挖掘的异步分布式机器学习框架
- 批准号:
2348159 - 财政年份:2023
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: IA: Collaborative Research: Intelligent Solutions for Navigating Big Data from the Arctic and Antarctic
BIGDATA:IA:协作研究:导航北极和南极大数据的智能解决方案
- 批准号:
2308649 - 财政年份:2022
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: Collaborative Research: F: Holistic Optimization of Data-Driven Applications
BIGDATA:协作研究:F:数据驱动应用程序的整体优化
- 批准号:
2027516 - 财政年份:2020
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: F: Collaborative Research: Practical Analysis of Large-Scale Data with Lyme Disease Case Study
BIGDATA:F:协作研究:莱姆病案例研究大规模数据的实际分析
- 批准号:
1934319 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: IA: Collaborative Research: Protecting Yourself from Wildfire Smoke: Big Data-Driven Adaptive Air Quality Prediction Methodologies
大数据:IA:协作研究:保护自己免受野火烟雾的侵害:大数据驱动的自适应空气质量预测方法
- 批准号:
1838022 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: F: Collaborative Research: Foundations of Responsible Data Management
大数据:F:协作研究:负责任的数据管理的基础
- 批准号:
1926250 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: IA: Collaborative Research: Intelligent Solutions for Navigating Big Data from the Arctic and Antarctic
BIGDATA:IA:协作研究:导航北极和南极大数据的智能解决方案
- 批准号:
1947584 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: IA: Collaborative Research: Asynchronous Distributed Machine Learning Framework for Multi-Site Collaborative Brain Big Data Mining
BIGDATA:IA:协作研究:用于多站点协作大脑大数据挖掘的异步分布式机器学习框架
- 批准号:
1837964 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: F: Collaborative Research: Optimizing Log-Structured-Merge-Based Big Data Management Systems
BIGDATA:F:协作研究:优化基于日志结构合并的大数据管理系统
- 批准号:
1838222 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant
BIGDATA: F: Collaborative Research: Optimizing Log-Structured-Merge-Based Big Data Management Systems
BIGDATA:F:协作研究:优化基于日志结构合并的大数据管理系统
- 批准号:
1838248 - 财政年份:2019
- 资助金额:
$ 39.45万 - 项目类别:
Standard Grant