Operator Learning Without the Adjoint

Explore cutting-edge research on operator learning techniques that eliminate the need for adjoint calculations in this 25-minute conference talk by Nicolas Boulle from the University of Cambridge. Delivered as part of the Fourth Symposium on Machine Learning and Dynamical Systems at the Fields Institute, gain insights into innovative approaches that could potentially revolutionize computational efficiency in machine learning and dynamical systems.

Operator Learning Without the Adjoint