Algebraic Geometry: A Window to Machine Learning
Workshop at IPAM explores algebraic geometry's role in advancing machine learning theory and applications, focusing on neural networks, feature learning, and interdisciplinary collaboration.
Funder: Institute for Pure and Applied Mathematics
Due Dates: December 9, 2026 (application deadline for fullest funding consideration)
Funding Amounts: Travel and registration support available; typical registration fees: $25–$100 depending on category; funding prioritized for early-career researchers.
Summary: Workshop supports researchers applying algebraic geometry to machine learning, with funding for attendance and registration.
Key Information: Funding requests must be indicated on the registration form; register early as space may be limited.
Description
This workshop convenes researchers in algebraic geometry and machine learning to develop new mathematical frameworks for understanding learning systems, with a particular focus on algebraic and geometric structures in neural networks. The event aims to advance theoretical understanding of phenomena such as feature learning, neural collapse, low-rank adaptation, and overparameterization, leveraging tools from computational algebra, tensor geometry, and semi-algebraic methods. The program fosters interdisciplinary collaboration between mathematicians and scientists, connecting pure mathematics with applications in trustworthy AI, compression, and privacy.
