Bridging Machine Learning, Dynamical Systems, and Algorithmic Information Theory: Insights from Sparse Kernel Flows, Poincaré Normal Forms and PDE Simplification

In this seminar talk, Dr. Boumediene Hamzi from CALTECH explores the intersection of machine learning, dynamical systems, and algorithmic information theory. Discover insights from sparse kernel flows, Poincaré normal forms, and PDE simplification techniques. The lecture is part of the "Representing, calibrating & leveraging prediction uncertainty from statistics to machine learning" event series at the Isaac Newton Institute. Join this hour-long presentation to understand how these mathematical disciplines connect and complement each other, offering new perspectives on complex systems modeling and analysis. The talk will take place on May 27th, 2025, from 10:30 to 11:30 at the Isaac Newton Institute, a prestigious research institute that attracts leading mathematical scientists from around the world.