Mathematical Foundations in Deep Learning and Generative AI (26w5572)

The Institute for Advanced Study in Mathematics will host the "Mathematical Foundations in Deep Learning and Generative AI" workshop in Hangzhou, China from August 30 to September 4, 2026.

Deep learning, especially generative AI, has transformed fields ranging from engineering to science. This success is largely due to advances in scalable computational platforms, both in hardware and software, and, even more critically, the availability of vast amounts of training data. While recent AI advancements have been primarily driven by empirical progress, we are now entering a phase where issues such as trustworthiness, scalability, fairness, privacy, reproducibility, and explainability are becoming crucial. Addressing these challenges is essential for the successful deployment of next-generation AI and data science that can truly benefit society.

Addressing these unresolved challenges requires fundamentally new ideas and approaches, demanding close collaboration among mathematicians, statisticians, computer scientists, and engineers. This workshop brings together an interdisciplinary group of outstanding scientists from around the world to present recent advancements, encourage new collaborations, and generate innovative solutions to the mathematical challenges involved in understanding deep learning and generative AI models.

The Institute for Advanced Study in Mathematics (IASM) in Hangzhou, China, and the Banff International Research Station for Mathematical Innovation and Discovery (BIRS) in Banff, are collaborative Canada-US-Mexico ventures that provide an environment for creative interaction as well as the exchange of ideas, knowledge, and methods within the Mathematical Sciences, with related disciplines and with industry. The research station in Banff is supported by Canada's Natural Science and Engineering Research Council (NSERC), the U.S. National Science Foundation (NSF) and Alberta Technology and Innovation.