Stabilizing Backpropagation Through Time to Learn Complex Physics

arXiv:2405.02041v1 Announce Type: new
Abstract: Of all the vector fields surrounding the minima of recurrent learning setups, the gradient field with its exploding and vanishing updates appears a poor choice for optimization, offering little beyond efficient computability. We seek to improve this suboptimal practice in the context of physics simulations, where backpropagating feedback through many unrolled time steps is considered crucial to acquiring temporally coherent behavior. The alternative vector field we propose follows from two principles: physics simulators, unlike neural …

arxiv backpropagation cs.lg learn physics physics.comp-ph through type