In recent years, rapid growth in theory and applications of machine learning have occurred. This growth has been driven by advances in deep learning, which has achieved tremendous success cracking difficult problems, such as large-scale image classification and reinforcement learning (e.g., mastering the game of Go). Despite this success, however, many theoretical and computational issues remain unresolved. At the same time, exciting new work is exploring connections between classical fields of mathematics, such as partial differential equations (PDEs), calculus of variations, optimal control/transport, and machine learning. These new insights hold the promise of addressing fundamental problems in machine learning and data science.
This Thematic Focus Period will gather a group of top experts in academia, industry, and government labs from the machine learning, PDEs, and the calculus of variations communities to discuss theoretical and computational issues and foster transdisciplinary collaboration.
Apply for a general membership to be in residence at the IMA for this program.