CIF: Medium: Collaborative Research: Information Theory and Statistical Inference from Large-Alphabet Data
CIF: Medium: Collaborative Research: Information Theory and Statistical Inference from Large-Alphabet Data
批准号:
1065622
负责人:
Alon Orlitsky
金额:
$41.86万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2011
资助国家:
美国
项目状态:
已结题
起止时间:
2011-08-01 至 2016-07-31
中文摘要
统计分析是许多具有挑战性的应用程序的关键,例如文本分类、语音识别和DNA分析。然而,通常可用的数据量与构成数据的符号(字母)集相当,甚至更小。不幸的是,在这个所谓的大字母表领域,我们对最佳推理知之甚少。最近,不同的科学团体开发了几种有前途的方法,包括统计学和机器学习中的贝叶斯非参数,信息论中的通用压缩,以及数学和计算机科学中的图极限理论。研究者们从这些多个角度来研究这个问题,但特别注重发展信息理论方法。研究了“模式最大似然”估计器的分析性质,该估计器在实践中表现良好,但在理论上还没有被理解,并对计算速度进行了探索。此外,它还试图描述贝叶斯非参数技术和模式方法可以更好地处理哪些问题类,并探索这些方法之间的联系。研究人员使用生成的理论进行自动文档分类,允许在存储、检索和分析数据方面实现更多的自动化。此外,研究人员利用该理论研究遗传变异,遗传变异与疾病诊断的联系是生物学系统量化的关键一步,在医学进步中发挥着越来越重要的作用。这项研究还为课堂带来了新的课程,通过夏威夷原住民科学与工程指导计划(Native Hawaiian Science and Engineering mentor Program)等特别的推广工作,让女性和代表性不足的少数族裔参与进来。
英文摘要
Statistical analysis is key to many challenging applications such as text classification, speech recognition, and DNA analysis. However, often the amount of data available is comparable or even smaller than the set of symbols (alphabet) constituting the data. Unfortunately, not much is known about optimal inference in this so-called large-alphabet domain. Recently, several promising approaches have been developed by different scientific communities, including Bayesian nonparametrics in statistics and machine learning, universal compression in information theory, and the theory of graph limits in mathematics and computer science.The investigators study the problem drawing from these multiple perspectives, but with a particular focus on developing the information theoretic approach. The research studies analytical properties of the "pattern maximum likelihood'' estimator, which performs well in practice but is not understood theoretically, and also explores computational speedups. Moreover, it attempts to delineate which problem classes are better handled by Bayesian nonparametric techniques and which by the pattern approach, and explores links between these approaches. The investigators use the resulting theory for automatic document classification, allowing for more automation in storing, retrieving, and analyzing data. Furthermore, the investigators use the theory to study genetic variations, whose link with disease diagnosis is a crucial step in the systematic quantification of biology that is playing an increasingly important role in medical advancement. The research also brings new courses to the classroom, with a special outreach effort to involve women and under-represented minorities, including through the Native Hawaiian Science and Engineering Mentorship Program.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
CIF: Student Travel Support for the 2017 IEEE International Symposium on Information Theory
-
批准号:1740960
-
项目类别:Standard Grant
-
资助金额:$2.0万
-
财政年份:2017
-
负责人:Alon Orlitsky
-
依托单位:
CIF: SMALL: Information Theoretic Foundations of Data Science
-
批准号:1619448
-
项目类别:Continuing Grant
-
资助金额:$50.0万
-
财政年份:2016
-
负责人:Alon Orlitsky
-
依托单位:
CIF: Medium: Collaborative Research: Learning in High Dimensions: From Theory to Data and Back
-
批准号:1564355
-
项目类别:Continuing Grant
-
资助金额:$59.85万
-
财政年份:2016
-
负责人:Alon Orlitsky
-
依托单位:
Enhancing Education and Awareness of Shannon Theory
-
批准号:1549515
-
项目类别:Standard Grant
-
资助金额:$29.99万
-
财政年份:2015
-
负责人:Alon Orlitsky
-
依托单位:
CIF: Small: Collaborative Research: Algorithms and Information-Theoretic Limits for Data-Limited Inference
-
批准号:1117765
-
项目类别:Standard Grant
-
资助金额:$23.64万
-
财政年份:2011
-
负责人:Alon Orlitsky
-
依托单位:
Collaborative Research: Design and Analysis of Compressed Sensing DNA Microarrays
-
批准号:0729029
-
项目类别:Continuing Grant
-
资助金额:$59.3万
-
财政年份:2007
-
负责人:Alon Orlitsky
-
依托单位:
Predicting the Unlikely: Theory, Algorithms, and Applications
-
批准号:0514973
-
项目类别:Standard Grant
-
资助金额:$0.0万
-
财政年份:2005
-
负责人:Alon Orlitsky
-
依托单位:
Universal Compression of Infinite Alphabets with Applications to Language Modeling
-
批准号:0313367
-
项目类别:Standard Grant
-
资助金额:$42.8万
-
财政年份:2003
-
负责人:Alon Orlitsky
-
依托单位:
Vector Quantization: Theoretical Limits and Practical Constructions
-
批准号:9815018
-
项目类别:Continuing Grant
-
资助金额:$17.5万
-
财政年份:1999
-
负责人:Alon Orlitsky
-
依托单位:
海外基金