Overview: The goal of this proposal is to create a multi-discipline and multi-institution collaborative institute in the Chicago area that focuses on key aspects of the theoretical foundations of data science. The institute will leverage existing strengths across computer science, statistics, economics, electrical engineering and operations research across Northwestern University, Toyota Technological Institute at Chicago (TTIC) and the University of Chicago to bear upon foundational problems related to machine learning, high-dimensional data analysis and optimization in both strategic and non-strategic environments. The research goals of the proposal will center around three broad themes: 1. High dimensional data analysis: This theme will address both algorithmic and statistical challenges in dealing with high dimensional data, and investigate topics like dimension reduction, metric embeddings, sketching, inference on networks and problems in unsupervised learning like clustering and probabilistic modeling. 2. Data Science in Strategic Environments: This will address computational and information theoretic challenges in econometric models of strategic behavior. Complexity arises, for example, from high-dimensional parameter spaces, unobserved heterogeneity, and multiplicity of equilibria in games. Specific topics of interest include inference on structural parameters, algorithms to characterize boundary of sets, partial identification, and machine learning in econometrics. 3. Machine learning and optimization: This theme will address foundational questions in both continuous and discrete optimization and its use in machine learning; topics include representation learning, robustness in learning, and provable bounds for non-convex optimization and deep learning.
|Effective start/end date||9/15/19 → 8/31/23|
- National Science Foundation (CCF-1934931 AMD001)
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.