Continuous Learned Primal Dual

arXiv:2405.02478v1 Announce Type: new
Abstract: Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be directly modelled by a parameterised ODE. This idea has had resounding success in the deep learning literature, with direct or indirect influence in many state of the art ideas, such as diffusion models or time dependant models. Recently, a continuous version of the U-net architecture …

abstract arxiv continuous cs.lg deep learning differential eess.iv literature network neural network ordinary primal success type