no code implementations • 28 Mar 2023 • Nick McGreivy, Ammar Hakim
Though this strategy is different from how standard solvers preserve invariants, it is necessary to retain the flexibility that allows machine learned solvers to be accurate at large $\Delta x$ and/or $\Delta t$.
no code implementations • 3 Nov 2022 • Tian Qin, Alex Beatson, Deniz Oktay, Nick McGreivy, Ryan P. Adams
Partial differential equations (PDEs) are often computationally challenging to solve, and in many settings many related PDEs must be be solved either at every timestep or for a variety of candidate boundary conditions, parameters, or geometric domains.
no code implementations • 10 Jun 2022 • Nick McGreivy, Ammar Hakim
This is because shift equivariance is a discrete symmetry while translation equivariance is a continuous symmetry.
1 code implementation • ICLR 2021 • Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P. Adams
The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives.