Solving High-Dimensional Partial Differential Equations Using Deep Learning

Explore the cutting-edge advancements in deep learning-based numerical algorithms for solving high-dimensional partial differential equations (PDEs) in this 54-minute conference talk by Jiequn Han at BIMSA. Gain insights into the progress made since 2017 in overcoming the curse of dimensionality across various applications. Discover a general procedural framework for these numerical innovations and delve into different formulations designed for high-dimensional scientific computing applications, ranging from the Deep BSDE method to the variational Monte Carlo method. Learn about promising future directions in this field and understand how these approaches are revolutionizing the solution of complex PDEs.

Jiequn Han: Solving high-dimensional partial differential equations using deep learning #ICBS2024