Level Crossing of Likelihood Functions in Sequential Decision Problems and Statistical Learning

顺序决策问题和统计学习中似然函数的水平交叉

基本信息

  • 批准号:
    1712657
  • 负责人:
  • 金额:
    $ 12.9万
  • 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:
    2017-07-01 至 2021-06-30
  • 项目状态:
    已结题

项目摘要

The last decade has witnessed remarkable progress in statistical methods for applications arising from various fields including education, psychology, finance, and engineering. The properties of many of these new methods remain unclear, calling for theoretical insights. This research project aims at (1) studying the theoretical underpinning of effective methods in statistical learning and sequential decision making and (2) developing new methods with provably efficiency and reliability. This research will not only address a class of fundamental problems in statistics but also have a positive impact on scientific research in other disciplines. One important application will be in the adaptive design of educational testing and personalized learning. Three types of problems will be considered in the project: information quantification for model selection, measuring the feasibility of classification, and sequential allocation. A common feature of the research problems involves handling the probability that a likelihood function exceeds a high level. The analysis of such a probability is statistically challenging, especially under the asymptotic regime where this probability decays at an exponential rate. Standard numerical evaluation tools, such as Monte Carlo methods, are computationally intensive to achieve a reasonable accuracy level for simulating such a small probability. Novel techniques will be developed to obtain sharp asymptotic approximations as well as provably efficient numerical methods simultaneously.
在过去的十年里,统计方法在教育、心理学、金融和工程等各个领域的应用取得了显着的进展。许多这些新方法的性质仍然不清楚,需要理论上的见解。本研究项目旨在(1)研究统计学习和顺序决策中有效方法的理论基础,(2)开发具有可证明的效率和可靠性的新方法。 这项研究不仅解决了统计学中的一类基本问题,而且对其他学科的科学研究也产生了积极的影响。一个重要的应用将是教育测试和个性化学习的自适应设计。本计画将考虑三种类型的问题:模型选择的资讯量化、衡量分类的可行性,以及循序分配。研究问题的一个共同特征涉及处理似然函数超过高水平的概率。这种概率的分析在统计上是具有挑战性的,特别是在这种概率以指数速率衰减的渐近状态下。标准的数值评估工具,如蒙特卡罗方法,是计算密集型的,以达到一个合理的精度水平,模拟这样一个小的概率。新的技术将被开发,以获得尖锐的渐近近似,以及证明有效的数值方法同时进行。

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 Note on Exploratory Item Factor Analysis by Singular Value Decomposition
  • DOI:
    10.1007/s11336-020-09704-7
  • 发表时间:
    2019-07
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Haoran Zhang;Yunxiao Chen;Xiaoou Li
  • 通讯作者:
    Haoran Zhang;Yunxiao Chen;Xiaoou Li
Structured Latent Factor Analysis for Large-scale Data: Identifiability, Estimability, and Their Implications
Sequential Hypothesis Test With Online Usage-Constrained Sensor Selection
  • DOI:
    10.1109/tit.2019.2910730
  • 发表时间:
    2016-01
  • 期刊:
  • 影响因子:
    2.5
  • 作者:
    Shang Li;Xiaoou Li;Xiaodong Wang;Jingchen Liu
  • 通讯作者:
    Shang Li;Xiaoou Li;Xiaodong Wang;Jingchen Liu
Robust Measurement via A Fused Latent and Graphical Item Response Theory Model
  • DOI:
    10.1007/s11336-018-9610-4
  • 发表时间:
    2018-09-01
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Chen, Yunxiao;Li, Xiaoou;Ying, Zhiliang
  • 通讯作者:
    Ying, Zhiliang
Moderate deviation for random elliptic PDE with small noise
小噪声随机椭圆偏微分方程的中等偏差
  • DOI:
    10.1214/17-aap1373
  • 发表时间:
    2018
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Li, Xiaoou;Liu, Jingchen;Lu, Jianfeng;Zhou, Xiang
  • 通讯作者:
    Zhou, Xiang
{{ 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 }}

Xiaoou Li其他文献

Submitted to the Annals of Applied Probability MODERATE DEVIATION FOR RANDOM ELLIPTIC PDE WITH SMALL NOISE By
提交给《应用概率年鉴》 具有小噪声的随机椭圆偏微分方程的中等偏差
  • DOI:
  • 发表时间:
    2017
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Xiaoou Li;Jingcheng Liu;Jianfeng Lu;Xiang Zhou
  • 通讯作者:
    Xiang Zhou
A Multi-objective transfer learning framework for time series forecasting with Concept Echo State Networks
一种基于概念回声状态网络的时间序列预测多目标迁移学习框架
  • DOI:
    10.1016/j.neunet.2025.107272
  • 发表时间:
    2025-06-01
  • 期刊:
  • 影响因子:
    6.300
  • 作者:
    Yingqin Zhu;Wen Yu;Xiaoou Li
  • 通讯作者:
    Xiaoou Li
Online fuzzy modeling with structure and parameter learning
  • DOI:
    10.1016/j.eswa.2008.09.016
  • 发表时间:
    2009-05-01
  • 期刊:
  • 影响因子:
  • 作者:
    Wen Yu;Xiaoou Li
  • 通讯作者:
    Xiaoou Li
Modelling of crude oil blending via discrete-time neural networks
通过离散时间神经网络进行原油混合建模
Discrete-time nonlinear system identification using recurrent neural networks
使用循环神经网络的离散时间非线性系统识别

Xiaoou Li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('Xiaoou Li', 18)}}的其他基金

CAREER: Detecting Structured Anomalies in Large-Scale Sequential Decision Problems and Latent Variable Models
职业:检测大规模序列决策问题和潜变量模型中的结构化异常
  • 批准号:
    2143844
  • 财政年份:
    2022
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Continuing Grant

相似国自然基金

Wall crossing现象和内禀Higgs态
  • 批准号:
    11305125
  • 批准年份:
    2013
  • 资助金额:
    22.0 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

Crossing the Finish Line: Intervening in a Critical Period for Educational Investment
冲过终点线:介入教育投资关键期
  • 批准号:
    2343873
  • 财政年份:
    2024
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Standard Grant
Motivic invariants and birational geometry of simple normal crossing degenerations
简单正态交叉退化的动机不变量和双有理几何
  • 批准号:
    EP/Z000955/1
  • 财政年份:
    2024
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Research Grant
ARCHCROP: Crossing Paths: Millet, Wheat and Cultural Exchanges in the Inner Asian Mountain Corridor, China
ARCHCROP:交叉路径:中国内亚山地走廊的小米、小麦和文化交流
  • 批准号:
    EP/Y027809/1
  • 财政年份:
    2024
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Fellowship
Unobtrusive Technologies for Secure and Seamless Border Crossing for Travel Facilitation
用于安全、无缝过境的低调技术,为旅行提供便利
  • 批准号:
    10070292
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    EU-Funded
The theoretical and practical study on the "boundary-crossing" nature of school education for social jusitice
学校社会正义教育“跨界”性的理论与实践研究
  • 批准号:
    23K02191
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Spinon band crossing and inversion in one-dimensional antiferromagnet
一维反铁磁体中的自旋子带交叉和反转
  • 批准号:
    23K03296
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Potential Driftwood Disaster Risk Assessment for River Crossing Bridges Based on AI Prediction of Driftwood Sources
基于漂流木来源AI预测的跨河桥梁潜在漂流木​​灾害风险评估
  • 批准号:
    23K04019
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Research on learning through boundary crossing in Japanese language education at the university
大学日语教育中的跨界学习研究
  • 批准号:
    23K12223
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Uncovering molecular factors driving sexual dimorphism in crossing over in diverse mouse genetic backgrounds
揭示不同小鼠遗传背景交叉中驱动性别二态性的分子因素
  • 批准号:
    10722746
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
Green Shipping Corridors: Feasibility of the world’s first hydrogen powered North Sea crossing
绿色航运走廊:世界上第一个氢动力穿越北海的可行性
  • 批准号:
    10039998
  • 财政年份:
    2023
  • 资助金额:
    $ 12.9万
  • 项目类别:
    Feasibility Studies
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了