Organized by: Michael R. Douglas, Sergei Gukov, James Halverson, Sven Krippendorf, and Fabian Ruehle
Recent years have seen great progress in data science (DS), specifically within the context of machine learning (ML) and artificial intelligence, which is beginning to lead to breakthroughs in mathematics and theoretical physics. In light of this growing subfield, this conference focuses on the application of DS techniques to string theory, topology, and geometry. Focus will be on applications of data science in three areas: string vacua, holography, and mathematical aspects of string theory. Topics include connections between geometric data and low energy effective theories, as well as their implications for particle physics and cosmology; directions in holography, including both formal relationships between deep learning and AdS / CFT, as well as application in real-world quantum field theory systems such as QCD; and applications in mathematical aspects of field theory and string theory, including the conformal bootstrap and knot theory. Previous progress will be highlighted and new research directions will be spurred.