Models and Theory for Multi-Task Operator Learning

Hayden Schaeffer
University of California, Los Angeles (UCLA)

PDEs are essential for describing a wide range of scientific phenomena and applications. Inferring solutions to spatiotemporal is often complex and computationally expensive due to their highly nonlinear and multiscale behavior, particularly in the presence of scarce or noisy measurements and incomplete model information. Recently, algorithms in multi-task operator learning have been proposed to improve predictions of spatiotemporal systems under these settings. This talk will focus on recent advances in multi-operator learning.


Back to Sampling, Inference, and Data-Driven Physical Modeling in Scientific Machine Learning