Developing Conjugate Models for Exact MCMC free Bayesian Inference with Application to High-Dimensional Spatio-Temporal Data
开发用于精确 MCMC 免费贝叶斯推理的共轭模型并应用于高维时空数据
基本信息
- 批准号:2310756
- 负责人:
- 金额:$ 22.73万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-09-01 至 2025-08-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
The massive expansion in the production of data has led to natural computational challenges in uncertainty quantification. In particular, Bayesian methodology can account for sources of uncertainty, but requires techniques known to be computationally demanding. These difficulties are exacerbated when data are spatially and/or temporally correlated. The current solutions predominantly use either approximations or inefficient iterative methods such as Markov chain Monte Carlo (MCMC). This project resolves the computational challenges in uncertainty quantification with novel statistical methodology that does not require approximations and MCMC. Big data has impacted nearly every area of science, and as a result, methodological development and software for scalable, exact, MCMC free Bayesian methodology will have a substantial effect. Not only will the proposed methodology and software be an advancement in statistics, but it will be useful across a broad range of disciplines that deal with complex spatio-temporal processes such as neuroscience, climatology, demography, econometrics, ecology, meteorology, oceanography, and official statistics. The investigator will educate and train graduate students, and disseminate project findings through journal publications, public-use software, and conference presentations.The objective of this project is to develop conjugate distribution theory for scalable Bayesian hierarchical models that create a larger framework for statisticians and subject matter scientist to perform MCMC free Bayesian inference without approximating the posterior distribution. In particular, this project will develop and extend the generalized conjugate multivariate (GCM) distribution, which allows one to simulate directly from the exact posterior distribution for a particular large class mixed effects models. This exact sample is referred to as Exact Posterior Regression (EPR). In Aim 1, the investigator will develop extensions of GCM and EPR to new settings including ordinal and nominal data, exact MCMC free inference for certain hyperparameters, and theoretical connections to existing statistical models. Aim 2 involves extensions of EPR to multivariate spatio-temporal and multiscale spatial data, allowing one to leverage several sources of dependence to improve predictions and perform spatial change of support (COS) without the use of MCMC or approximate Bayesian methods. To achieve scalability, in Aim 3, the investigator will develop an exact Bayesian hierarchical model that repeatedly subsets the data in an informative manner that does not impose additional assumptions on the data.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.
数据生产的大规模扩张导致了不确定性量化的自然计算挑战。特别是,贝叶斯方法可以解释不确定性的来源,但需要已知的计算要求高的技术。当数据在空间和/或时间上相关时,这些困难加剧。目前的解决方案主要使用近似或低效的迭代方法,如马尔可夫链蒙特卡罗(MCMC)。该项目解决了不确定性量化的计算挑战,新的统计方法,不需要近似和MCMC。大数据已经影响了几乎所有的科学领域,因此,可扩展的、精确的、不含MCMC的贝叶斯方法的方法论开发和软件将产生重大影响。所提出的方法和软件不仅将是统计学的进步,而且将在处理复杂时空过程的广泛学科中发挥作用,如神经科学,气候学,人口学,计量经济学,生态学,气象学,海洋学和官方统计。研究人员将教育和培训研究生,并通过期刊出版物,公共使用的软件和会议演示来传播项目成果。该项目的目标是为可扩展的贝叶斯分层模型开发共轭分布理论,为统计学家和主题科学家创建一个更大的框架,以执行MCMC自由贝叶斯推断而无需近似后验分布。特别是,该项目将开发和扩展广义共轭多变量(GCM)分布,它允许人们直接从特定大类混合效应模型的精确后验分布进行模拟。这个精确的样本被称为精确后验回归(EPR)。在目标1中,研究人员将开发GCM和EPR的扩展到新的设置,包括有序和名义数据,某些超参数的精确MCMC自由推断,以及与现有统计模型的理论联系。 目标2涉及EPR的扩展到多变量时空和多尺度空间数据,允许利用几个来源的依赖,以改善预测和执行空间变化的支持(COS),而不使用MCMC或近似贝叶斯方法。为了实现可扩展性,在目标3中,研究人员将开发一个精确的贝叶斯分层模型,该模型以信息丰富的方式反复对数据进行子集化,而不会对数据施加额外的假设。该奖项反映了NSF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。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Jonathan Bradley其他文献
Friedreich's ataxia.
弗里德赖希共济失调。
- DOI:
10.1016/s0074-7742(02)53006-3 - 发表时间:
2002 - 期刊:
- 影响因子:0
- 作者:
JM Cooper;Jonathan Bradley - 通讯作者:
Jonathan Bradley
Receptors that couple to 2 classes of G proteins increase cAMP and activate CFTR expressed in Xenopus oocytes.
与 2 类 G 蛋白偶联的受体会增加 cAMP 并激活非洲爪蟾卵母细胞中表达的 CFTR。
- DOI:
- 发表时间:
1993 - 期刊:
- 影响因子:0
- 作者:
Y. Uezono;Jonathan Bradley;Churl Min;N. McCarty;Michael W. Quick;J. Riordan;C. Chavkin;K. Zinn;Henry A. Lester;Norman Davidson - 通讯作者:
Norman Davidson
Identification and organization of a postural anti-gravity module in the cerebellar vermis
小脑蚓部姿势反重力模块的识别和组织
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:3.3
- 作者:
Aurélien Gouhier;Vincent Villette;Benjamin Mathieu;Annick Ayon;Jonathan Bradley;S. Dieudonné - 通讯作者:
S. Dieudonné
A Fiberscope for Spatially Selective Photoactivation and Functional Fluorescence Imaging in Freely-Behaving Mice
用于自由行为小鼠的空间选择性光激活和功能荧光成像的纤维镜
- DOI:
10.1364/brain.2015.brw1b.1 - 发表时间:
2015 - 期刊:
- 影响因子:14.5
- 作者:
C. Ventalon;V. Szabo;V. D. Sars;Jonathan Bradley;V. Emiliani - 通讯作者:
V. Emiliani
A fast and responsive voltage indicator with enhanced sensitivity for unitary synaptic events
- DOI:
10.1016/j.neuron.2024.08.019 - 发表时间:
2024-11-20 - 期刊:
- 影响因子:
- 作者:
Yukun A. Hao;Sungmoo Lee;Richard H. Roth;Silvia Natale;Laura Gomez;Jiannis Taxidis;Philipp S. O’Neill;Vincent Villette;Jonathan Bradley;Zeguan Wang;Dongyun Jiang;Guofeng Zhang;Mengjun Sheng;Di Lu;Edward Boyden;Igor Delvendahl;Peyman Golshani;Marius Wernig;Daniel E. Feldman;Na Ji - 通讯作者:
Na Ji
Jonathan Bradley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('Jonathan Bradley', 18)}}的其他基金
Collaborative Research: Multi-distribution, Multivariate, and Multiscale Spatio-Temporal Models with Applications to Official Statistics
合作研究:多分布、多变量、多尺度时空模型及其在官方统计中的应用
- 批准号:
1853099 - 财政年份:2019
- 资助金额:
$ 22.73万 - 项目类别:
Standard Grant
相似海外基金
A Conditionally Activable Small Molecule Pro-Drug Conjugate for Targeted Treatment of Pancreatic Cancer
用于胰腺癌靶向治疗的条件激活小分子前药偶联物
- 批准号:
EP/Y036336/1 - 财政年份:2024
- 资助金额:
$ 22.73万 - 项目类别:
Research Grant
Pharmacokinetic analysis of antibody drug conjugate in tumor cells utilizing synchrotron soft X-ray imaging
利用同步加速器软 X 射线成像对肿瘤细胞中抗体药物偶联物进行药代动力学分析
- 批准号:
23H03716 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
A Novel VpreB1 Anti-body Drug Conjugate for the Treatment of B-Lineage Acute Lymphoblastic Leukemia/Lymphoma
一种用于治疗 B 系急性淋巴细胞白血病/淋巴瘤的新型 VpreB1 抗体药物偶联物
- 批准号:
10651082 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
Studies on the development of antibody-drug conjugate orphan drugs based on photodynamic therapy targeting oral cancer.
基于口腔癌光动力疗法的抗体药物偶联孤儿药的开发研究。
- 批准号:
23K09344 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
An Aptamer-directed IgG1-Fc Drug Conjugate (AFDC) for Treating Pancreatic Cancer
用于治疗胰腺癌的适体导向 IgG1-Fc 药物偶联物 (AFDC)
- 批准号:
10761053 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
An IGF-1R-targeting peptide drug conjugate for targeted treatment of atypical teratoid/rhabdoid tumors
用于靶向治疗非典型畸胎瘤/横纹肌样瘤的 IGF-1R 靶向肽药物缀合物
- 批准号:
10760549 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
O-polysaccharide (OPS)-IpaB Conjugate Vaccine to Prevent Shigellosis
O-多糖 (OPS)-IpaB 结合疫苗预防志贺氏菌病
- 批准号:
10704815 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
OPP-PRF: Conjugate Experiment to Explore Magnetospheric Phenomena Via Spatial Sonification and Mixed Reality
OPP-PRF:通过空间超声和混合现实探索磁层现象的共轭实验
- 批准号:
2218996 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
Continuing Grant
Dual-payload antibody-drug conjugate for chemo-immunotherapy of triple-negative breast cancers
用于三阴性乳腺癌化学免疫治疗的双有效负载抗体-药物偶联物
- 批准号:
10711488 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
LPS conjugate for Coxiella
柯克斯体 LPS 结合物
- 批准号:
10086008 - 财政年份:2023
- 资助金额:
$ 22.73万 - 项目类别:
Small Business Research Initiative