Back to publications
Continuous Learned Primal Dual
Paper Details
Published: 2024/05/03
DOI: 10.48550/arXiv.2405.02478
ARXIV ID: 2405.02478v1
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. The authors propose an upgrade to the well known primal dual method for reconstruction, using the literature of neural ODEs, to interpret the network as solving an ODE rather than a set of discrete steps.
