Interface of Statistical Learning and Optimal Decisions
Interface of Statistical Learning and Optimal Decisions
批准号:
2210833
负责人:
Jianqing Fan
金额:
$50.0万
依托单位:
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2022
资助国家:
美国
项目状态:
未结题
起止时间:
2022-07-01 至 2026-06-30
中文摘要
在生物、自然、社会科学和工程领域,大量数据集被常规收集,并对统计分析、个性化治疗和决策产生了巨大影响。这些成功背后的驱动引擎是深度学习的表示能力和马尔可夫决策过程的动态策略优化框架,以及大数据的可用性。然而,训练算法仍然需要大量的时间和计算能力,而统计和算法效率也仍然知之甚少。该项目的目的是理解和改进用于深度学习、强化学习和大数据分析的统计方法,重点是统计建模和最优策略学习之间的接口。它旨在推进人工智能研究、自动驾驶和控制、电子商务、分子机制、生物过程、遗传关联、大脑功能以及经济和金融风险方面的知识。本项目将通过与本科生、研究生和博士后的紧密合作,将研究与教育结合起来,并开发具有良好理论支持的公开计算机软件。该项目旨在开发和理解深度学习中使用的各种新的统计方法,引入统计建模和学习技术来增强强化学习中的策略优化,并解决大数据分析中的几个重要问题。第一个目标是提供对深度学习中使用的各种技术的理论理解。研究者将研究过度参数化在非线性模型和低秩矩阵恢复中的作用,理解最小范数插值并阐明神经网络模型与数据分布尾部之间的相互作用。第二个目标是研究统计建模和最优决策之间的接口。研究者计划使用半参数模型和结构化非参数模型研究上下文动态定价,并从自适应函数近似的角度使用分层组合模型揭示支撑深度强化学习成功的统计理论。研究者还将为政策学习引入新的降维技术和理论,以提高统计和算法效率。第三个目标是解决大数据分析中的几个风格化问题。这些包括马尔可夫依赖性、缺失数据、高度相关的测量、删减的响应和分布式数据等。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。
英文摘要
Massive datasets are routinely collected in the fields of biological, natural, and social sciences, and engineering and have had a huge impact on statistical analysis, personalized treatments, and decision-making. The driving engines behind these successes are the representation power of deep learning and the dynamic policy optimization framework of Markov decision processes, in addition to the availability of big data. However, training algorithms still take enormous amounts of time and computing power, while statistical and algorithmic efficiencies are also still poorly understood. The aim of this project is to understand and improve statistical methods used in deep learning, reinforcement learning, and big data analysis, with an emphasis on the interfaces between statistical modeling and optimal policy learning. It aims to advance knowledge in AI research, automatic driving and control, e-commerce, molecular mechanisms, biological processes, genetic associations, brain functions, and economic and financial risks. The project will integrate research and education by working closely with undergraduate students, graduate students, and postdoctoral fellows, and develop publicly available computer software with sound theoretical support.The project aims at developing and understanding various new statistical methods used in deep learning, introducing statistical modeling and learning techniques to enhance policy optimization in reinforcement learning, and addressing several important issues in the analysis of big data. The first aim is to provide a theoretical understanding of various techniques used in deep learning. The investigator will study the role of over-parametrization in nonlinear models and low-rank matrix recoveries, understanding minimum norm interpolation and elucidating the interactions between neural network models and the tails of the data distribution. The second aim is to study the interface between statistical modeling and optimal decision. The investigator plans to study contextual dynamic pricing using semiparametric models and structured nonparametric models and to unveil the statistical theory that underpins the success of deep reinforcement learning from an adaptive function approximation point of view using hierarchical composition models. The investigator will also introduce new dimensionality reduction techniques and theories for policy learning to improve both statistical and algorithmic efficiencies. The third aim is to address several stylized issues in big data analytics. These include Markovian dependence, missing data, highly correlated measurements, censored responses, and distributed data, among others.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.
期刊论文(2)
专著(0)
科研奖励(0)
会议论文
DOI:
10.1080/01621459.2022.2128359
发表时间:
2021-09
期刊:
CompSciRN: Other Machine Learning (Topic)
影响因子:
--
作者:
[Jianqing Fan;Yongyi Guo;Mengxin Yu]
通讯作者:
Jianqing Fan;Yongyi Guo;Mengxin Yu
DMS/NIGMS 2: Collaborative Research: Developing Statistical Learning Methods for Revealing the Molecular Signatures of Microvascular Changes in Neural Injury
-
批准号:2053832
-
项目类别:Continuing Grant
-
资助金额:$45.0万
-
财政年份:2021
-
负责人:Jianqing Fan
-
依托单位:
FRG: Collaborative Research: Flexible Network Inference
-
批准号:2052926
-
项目类别:Standard Grant
-
资助金额:$23.0万
-
财政年份:2021
-
负责人:Jianqing Fan
-
依托单位:
Collaborative Research: Statistical Methods for RNA-seq Based Transcriptomic Analysis of Macrophage Function in Spinal Cord Injury
-
批准号:1662139
-
项目类别:Continuing Grant
-
资助金额:$80.0万
-
财政年份:2017
-
负责人:Jianqing Fan
-
依托单位:
Robust and Distributed Statistical Learning from Big Data
-
批准号:1712591
-
项目类别:Continuing Grant
-
资助金额:$60.0万
-
财政年份:2017
-
负责人:Jianqing Fan
-
依托单位:
Collaborative Research: Interface of Probability and Statistics for High-dimensional Inference
-
批准号:1406266
-
项目类别:Continuing Grant
-
资助金额:$40.0万
-
财政年份:2014
-
负责人:Jianqing Fan
-
依托单位:
Statistical Inferences on Massive Data
-
批准号:1206464
-
项目类别:Continuing Grant
-
资助金额:$60.0万
-
财政年份:2012
-
负责人:Jianqing Fan
-
依托单位:
Workshop on: Discovery in Complex or Massive Datasets: Common Statistical Themes
-
批准号:0751568
-
项目类别:Standard Grant
-
资助金额:$4.55万
-
财政年份:2007
-
负责人:Jianqing Fan
-
依托单位:
Collaborative Research: Development of bioinformatic methods for studying gene expression network inflammation and neuronal regeneration
-
批准号:0714554
-
项目类别:Continuing Grant
-
资助金额:$61.0万
-
财政年份:2007
-
负责人:Jianqing Fan
-
依托单位:
High-dimensional statistical learning and inference
-
批准号:0704337
-
项目类别:Continuing Grant
-
资助金额:$92.0万
-
财政年份:2007
-
负责人:Jianqing Fan
-
依托单位:
Workshop on Frontiers of Statistics: Nonparametric Modeling of Complex Data
-
批准号:0531839
-
项目类别:Standard Grant
-
资助金额:$1.6万
-
财政年份:2006
-
负责人:Jianqing Fan
-
依托单位:
Nonparametric transition based-tests for Markov processes in financial econometrics
-
批准号:0532370
-
项目类别:Standard Grant
-
资助金额:$40.0万
-
财政年份:2005
-
负责人:Jianqing Fan
-
依托单位:
Collaborative Research: FRG: New development on nonparametric modeling and inferences with biological applications
-
批准号:0354223
-
项目类别:Standard Grant
-
资助金额:$55.2万
-
财政年份:2004
-
负责人:Jianqing Fan
-
依托单位:
Inferences for Multivariate Semiparametric and Nonparametric Models with Applications to Risk Management
-
批准号:0355179
-
项目类别:Standard Grant
-
资助金额:$17.58万
-
财政年份:2003
-
负责人:Jianqing Fan
-
依托单位:
Inferences for Multivariate Semiparametric and Nonparametric Models with Applications to Risk Management
-
批准号:0204329
-
项目类别:Standard Grant
-
资助金额:$22.5万
-
财政年份:2002
-
负责人:Jianqing Fan
-
依托单位:
Data-Analytic Modeling for High-Dimensional Data
-
批准号:0196041
-
项目类别:Continuing Grant
-
资助金额:$8.56万
-
财政年份:2000
-
负责人:Jianqing Fan
-
依托单位:
Scientific Computing Research Environments for the Mathematical Sciences (SCREMS)
-
批准号:9977096
-
项目类别:Standard Grant
-
资助金额:$3.0万
-
财政年份:1999
-
负责人:Jianqing Fan
-
依托单位:
Data-Analytic Modeling for High-Dimensional Data
-
批准号:9803200
-
项目类别:Continuing Grant
-
资助金额:$8.56万
-
财政年份:1998
-
负责人:Jianqing Fan
-
依托单位:
Mathematical Sciences Computing Research Environments
-
批准号:9506575
-
项目类别:Standard Grant
-
资助金额:$4.31万
-
财政年份:1995
-
负责人:Jianqing Fan
-
依托单位:
Mathematical Sciences: Processing Massive Noisy Data with Hidden Structure
-
批准号:9504414
-
项目类别:Continuing Grant
-
资助金额:$15.7万
-
财政年份:1995
-
负责人:Jianqing Fan
-
依托单位:
Mathematical Sciences:Postdoctoral Research Fellowship
-
批准号:9306063
-
项目类别:Fellowship Award
-
资助金额:$7.5万
-
财政年份:1993
-
负责人:Jianqing Fan
-
依托单位:
海外基金