Data Science and Decisions: Dynamical, Statistical and Economic Perspectives

• Activity Number: 97 - Introductory Overview Lecture: New Frontiers in Machine Learning: Beyond Prediction and on to Consequential Decision Making
• Type: Invited
• Date/Time: Monday, August 3, 2020 : 1:00 PM to 2:50 PM
• Sponsor: JSM Partner Societies
• Author(s): Michael I. Jordan*
• Companies: University of California, Berkeley
• Keywords: data science; machine learning; game theory; decision-making; optimization; sampling

Abstract

While there has been significant progress at the interface of statistics and computer science in recent years, many fundamental challenges remain, often arising from emerging problems in technology. Some are mathematical and algorithmic in nature, such as the challenges associated with optimization and sampling in high-dimensional spaces. Some are statistical, including the challenges associated with multiple decision-making in sequential settings. Others are economic in nature, including the need to cope with scarcity and provide incentives in learning-based multi-way markets. I will present recent progress on each of these fronts and will discuss open challenges.