HDR TRIPODS: UIC Foundations of Data Science Institute

HDR TRIPODS：UIC 数据科学研究所基础

• 批准号: 1934915
• 负责人: Lev Reyzin
• 金额: $ 150万
• 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: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1934915&HistoricalAwards=false
• 关键词: HDR; TRIPODS; UIC; Foundations; Data

The project creates a collaborative research institute combining aspects of mathematics, statistics, computer science, and engineering to study the foundations of data science at the University of Illinois at Chicago (UIC). The institute will be a collaboration between three departments: Computer Science (CS), Mathematics, Statistics, and Computer Science (MSCS), and Electrical and Computer Engineering (ECE). The institute will leverage the wide range of expertise among the investigators on this project in the three departments to bring the theoretical foundations of data science closer to the practice of data science. This involves studying idealized models of data, understanding inherent computational limits associated to these idealized models, and then developing models and methods that are robust to realistic models of uncertainty. The institute will also focus on training the next generation of researchers and will leverage the diversity of UIC, a large urban public research-intensive university with one of the most diverse student bodies in the country.The research aims to push the boundaries of the theory of data science by both gaining deeper understanding of idealized models and by building a theory around realistic models of data and computation. The themes pursued by this institute will include 1) the representation and structure of data; 2) machine learning and complexity; and 3) robustness and privacy. These themes will serve to link the theory and application of data science and to provide opportunities for the investigators to pool their expertise across the three disciplines of theoretical computer science, mathematical sciences, and electrical engineering. The specific activities of the research institute will include hosting themed research workshops, developing the UIC data science curriculum across the three departments, and fostering regional and industrial collaborations through partnerships with the Midwest Big Data Hub and the Discovery Partners Institute. Broader impacts of the institute will include applications of the proposed research to practical data science problems, the development of interdisciplinary data science courses spanning multiple departments, and increasing participation, especially of underrepresented groups, by broadly recruiting students from UIC's diverse community to study data science.This project is part of the National Science Foundation's Harnessing the Data Revolution (HDR) Big Idea activity.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.

该项目创建了一个合作研究所，结合了数学，统计学，计算机科学和工程学方面，在芝加哥伊利诺伊大学（UIC）研究数据科学的基础。 该研究所将是三个部门之间的合作：计算机科学（CS），数学，统计和计算机科学（MSCS），以及电气和计算机工程（ECE）。该研究所将利用三个部门的研究人员在该项目上的广泛专业知识，使数据科学的理论基础更接近数据科学的实践。 这涉及研究理想化的数据模型，理解与这些理想化模型相关的固有计算限制，然后开发对现实不确定性模型具有鲁棒性的模型和方法。 该研究所还将专注于培养下一代研究人员，并将利用UIC的多样性，UIC是一所大型城市公立研究密集型大学，拥有全国最多样化的学生群体之一。该研究旨在通过加深对理想化模型的理解并围绕数据和计算的现实模型构建理论来推动数据科学理论的边界。 该研究所追求的主题将包括：1）数据的表示和结构; 2）机器学习和复杂性; 3）鲁棒性和隐私。 这些主题将有助于将数据科学的理论和应用联系起来，并为研究人员提供机会，将他们的专业知识汇集在理论计算机科学，数学科学和电气工程这三个学科中。 该研究所的具体活动将包括举办主题研究研讨会，开发跨三个部门的UIC数据科学课程，并通过与中西部大数据中心和Discovery Partners Institute的合作促进区域和行业合作。 该研究所更广泛的影响将包括将拟议的研究应用于实际的数据科学问题，开发跨越多个部门的跨学科数据科学课程，以及增加参与，特别是代表性不足的群体，通过广泛招募UIC多元化社区的学生来学习数据科学。该项目是国家科学基金会利用数据革命（HDR）的一部分大创意活动。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

Decomposing the Training of Deep Learned Turbo codes via a Feasible MAP Decoder

通过可行的 MAP 解码器分解深度学习 Turbo 码的训练

• DOI: 10.1109/istc57237.2023.10273550
• 发表时间: 2023
• 期刊: IEEE
• 作者: Mulgund, A.;Devroye, N.;Turán, Gy.;Žefran, M.
• 通讯作者: Žefran, M.

On biased random walks, corrupted intervals, and learning under adversarial design

• DOI: 10.1007/s10472-020-09696-1
• 发表时间: 2020-03
• 期刊: Annals of Mathematics and Artificial Intelligence
• 影响因子: 1.2
• 作者: D. Berend;A. Kontorovich;L. Reyzin;Thomas Robinson

On the Geometry of Stable Steiner Tree Instances

关于稳定斯坦纳树实例的几何结构

• 发表时间: 2022
• 期刊: Canadian Conference on Computational Geometry
• 作者: Freitag, James;Mohammadi, Neshat;Potukuchi, Aditya;Reyzin, Lev
• 通讯作者: Reyzin, Lev

Combining No-regret and Q-learning

结合无悔和 Q 学习

• DOI: 10.5555/3398761.3398833
• 发表时间: 2020
• 期刊: AAMAS Conference proceedings
• 作者: Kash, Ian A.;Sullins, Michael;Hofmann, Katja
• 通讯作者: Hofmann, Katja

Approximately counting independent sets in bipartite graphs via graph containers

通过图容器近似计算二分图中的独立集

• DOI: 10.1137/1.9781611977073.24
• 发表时间: 2022
• 期刊: Proceedings of the 2022 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA
• 作者: Jenssen, Matthew;Perkins, Will;Potukuchi, Aditya
• 通讯作者: Potukuchi, Aditya