Institute for Data, Econometrics, Algorithms and Learning (IDEAL)

数据、计量经济学、算法和学习研究所 (IDEAL)

• 批准号: 2217023
• 负责人: Lev Reyzin
• 金额: $ 318万
• 依托单位: University of Illinois at Chicago
• 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
• 起止时间: 2022-09-01 至 2027-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2217023&HistoricalAwards=false
• 关键词: Institute; Data; Econometrics; Algorithms; Learning

The Institute for Data, Econometrics, Algorithms, and Learning (IDEAL) will consolidate and amplify research devoted to the foundations of data science across all the major research-focused educational institutions in the greater Chicago area: the University of Illinois at Chicago, Northwestern University, the Toyota Technological Institute at Chicago, the University of Chicago, and the Illinois Institute of Technology. This transdisciplinary institute involves over 50 researchers working on key aspects of the foundations of data science across computer science, electrical engineering, mathematics, statistics, and several related fields like economics, operations research, and law, and they are complemented by members of Google’s learning theory team. Its research goals range from the core foundations of data science to its interfaces with other disciplines: 1) tackling important challenges related to foundations of machine learning and optimization, 2) addressing statistical, algorithmic and mathematical challenges in dealing with high-dimensional data, and 3) exploring the foundations of aspects of data science that interact with society. The institute will foster strong connections with the community and local high schools, broaden participation in data science locally and nationally, and build lasting research and educational infrastructure through its activities. Institute activities will include workshops for undergraduate students, high school teacher workshops, public lectures, and museum exhibit designs. These will build new pathways for undergraduate students, high school students, and the broader public from diverse and underrepresented backgrounds, to increase participation and engagement with scientific fields related to data science.The research thrusts of the institute will center around the foundations of machine learning, high-dimensional data analysis and inference, and data science and society. Specific topics include foundations of deep learning, reinforcement learning, machine learning and logic, network inference, high-dimensional data analysis, trustworthiness & reliability, fairness, and data science with strategic agents. The research activities are designed to facilitate collaboration between the different disciplines and across the five Chicago-area institutions, and they build on the extensive experience from previous efforts of the participating universities. The activities include topical special programs, postdoctoral fellows, co-mentored PhD students, workshops, coordinated graduate courses, visiting fellows, research meetings, and brainstorming sessions. The proposed research will lead to new theoretical frameworks, models, mathematical tools and algorithms for analyzing high-dimensional data, inference and learning. Successful outcomes will also lead to a better understanding of the foundations of data science and machine learning in both strategic and non-strategic environments – including emerging concerns like reliability, fairness, privacy and interpretability as data science interacts with society in various ways. The institute will also have broader impacts of strengthening research and educational infrastructure, developing human resources, broadening participation from underrepresented groups, and by connecting theory to science and industry. The institute will organize activities to engage the community and a diverse group of students at all levels, including introductory workshops for undergraduate research participants, high school student and teacher outreach (through a partnership with the Math Circles of Chicago), and public lectures as part of both our research program and a partnership with the Museum of Science and Industry. The Chicago public institutions that we engage serve a very diverse population, so the outreach, recruitment, and training activities will broaden participation from underrepresented groups. Finally, the institute will have direct engagement with applications and industry through its activities involving Google, other industry partners in the broader Chicago area, and applied data science institutes.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、计量经济学、算法和学习研究所（IDEAL）将巩固和扩大大芝加哥地区所有主要研究型教育机构的数据科学基础研究：伊利诺伊大学芝加哥分校、西北大学、芝加哥丰田技术研究所、芝加哥大学和伊利诺伊理工学院。这个跨学科研究所涉及50多名研究人员，他们致力于数据科学基础的关键方面，包括计算机科学，电气工程，数学，统计学以及经济学，运筹学和法律等几个相关领域，并由Google的学习理论团队成员补充。它的研究目标从数据科学的核心基础到与其他学科的接口：1）解决与机器学习和优化基础相关的重要挑战，2）解决处理高维数据的统计，算法和数学挑战，以及3）探索与社会互动的数据科学方面的基础。该研究所将促进与社区和当地高中的紧密联系，扩大当地和全国对数据科学的参与，并通过其活动建立持久的研究和教育基础设施。研究所的活动将包括本科生研讨会，高中教师研讨会，公开讲座和博物馆展览设计。这些将为本科生、高中生以及来自多元化和代表性不足背景的更广泛公众建立新的途径，以增加对数据科学相关科学领域的参与和参与。该研究所的研究重点将围绕机器学习的基础、高维数据分析和推理以及数据科学与社会。具体主题包括深度学习，强化学习，机器学习和逻辑，网络推理，高维数据分析，可信度可靠性，公平性和数据科学与战略代理的基础。这些研究活动旨在促进不同学科之间以及芝加哥地区五个机构之间的合作，并建立在参与大学以前努力的丰富经验基础上。这些活动包括专题特别计划，博士后研究员，共同指导的博士生，研讨会，协调研究生课程，访问学者，研究会议和头脑风暴会议。拟议的研究将为分析高维数据、推理和学习带来新的理论框架、模型、数学工具和算法。成功的成果还将使人们更好地理解数据科学和机器学习在战略和非战略环境中的基础，包括随着数据科学以各种方式与社会互动而出现的可靠性、公平性、隐私性和可解释性等新问题。该研究所还将在加强研究和教育基础设施、开发人力资源、扩大代表性不足群体的参与以及将理论与科学和工业联系起来等方面产生更广泛的影响。该研究所将组织活动，让社区和各级学生的多元化群体参与，包括本科研究参与者的介绍性研讨会，高中学生和教师推广（通过与芝加哥数学界的合作伙伴关系），以及作为我们研究计划和与科学与工业博物馆合作伙伴关系的一部分的公开讲座。我们参与的芝加哥公共机构为非常多样化的人口提供服务，因此推广，招聘和培训活动将扩大代表性不足的群体的参与。最后，该研究所将通过与谷歌、芝加哥地区的其他行业合作伙伴以及应用数据科学研究所开展的活动，直接参与应用和行业。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力审查标准进行评估，被认为值得支持。

项目成果

Interpreting Training Aspects of Deep-Learned Error-Correcting Codes

解释深度学习纠错码的训练方面

• 发表时间: 2023
• 期刊: International Symposium on Information Theory
• 作者: Devroye, Natasha;Mulgund, Abhijeet;Shekhar, Raj;Turan, Gyorgy;Zefran, Milos;Zhou, Yingyao
• 通讯作者: Zhou, Yingyao