The primary activity of the institute are thematically focused quarters which will coordinate graduate course work, visiting predoctoral fellows, workshops, and external visitors.
Are you either a current participant or someone looking to participate in the special quarters? Find out more about joining in on the participate page.
Inference and Data Science on Networks
March 30 – June 6, 2020
Over the past decade or so, many diverse communities have become increasingly interested in networks as a way of understanding the role of interconnections between various entities.
Theory of Deep Learning
September 21 – December 5, 2020
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.
Algorithms for Partially Identified Models
Empirical analysis in economics most often involves a model that describes how agents behave in a market, data on their actions and characteristics, and a set of assumptions. The partial identification approach to econometrics recognizes that some assumptions are plausible – e.g., based on economic principles that respect optimizing behavior – while some are made out of convenience.
Robustness in High-dimensional Statistics
Today’s data pose unprecedented challenges to statisticians and data analysts. It may be incomplete, corrupted, or exposed to some unknown source of contamination. We need new methods and theories to grapple with these challenges.
High Dimensional Data Analysis
Today, machine learning and data science deal with tremendous amounts of high-dimensional data. Processing these data requires extensive computational resources (these often include large CPU and GPU clusters). It is expected that the amount of collected and analyzed data will grow significantly in the coming years.
Incentives in Shared Data Infrastructure
Data analysis is playing an increasingly central role in many scientific disciplines, engineering advances, commercial enterprises, and processes with societal implications. In many of these applications, data is becoming a precious resource that is generated, shared, stored and analyzed by multiple individuals with differing motivations, interests, coordination and levels of trust in each other.