30
0

Scalable physical source-to-field inference with hypernetworks

Abstract

We present a generative model that amortises computation for the field around e.g. gravitational or magnetic sources. Exact numerical calculation has either computational complexity O(M×N)\mathcal{O}(M\times{}N) in the number of sources and field evaluation points, or requires a fixed evaluation grid to exploit fast Fourier transforms. Using an architecture where a hypernetwork produces an implicit representation of the field around a source collection, our model instead performs as O(M+N)\mathcal{O}(M + N), achieves accuracy of  ⁣4%6%\sim\!4\%-6\%, and allows evaluation at arbitrary locations for arbitrary numbers of sources, greatly increasing the speed of e.g. physics simulations. We also examine a model relating to the physical properties of the output field and develop two-dimensional examples to demonstrate its application. The code for these models and experiments is available at https://github.com/cmt-dtu-energy/hypermagnetics.

View on arXiv
Comments on this paper