Synopsis: Deep learning plays a central role in the recent revolution of artificial intelligence and data science. In a wide range of applications, such as computer vision, natural language processing, and robotics, deep learning achieves dramatic performance improvements over existing baselines and even human. Despite the empirical success of deep learning, its theoretical foundation remains less understood, which hinders the development of more principled methods with performance guarantees.

About IDEAL: IDEAL is an NSF-funded multi-discipline (computer science, statistics, economics, electrical engineering, and operations research) and multi-institution (Northwestern University, Toyota Technological Institute at Chicago, and University of Chicago) collaborative institute that focuses on key aspects of the theoretical foundations of machine learning, high-dimensional data analysis, and optimization in both strategic and non-strategic environments. The primary activity of the institute will be thematically focused quarters which will coordinate graduate course work with workshops and external visitors.

This Special Quarter is organized by Nathan Srebro (TTIC), Zhaoran Wang (Northwestern), and Dongning Guo (Northwestern).