google-research/torchsde

Can I implement Neural ODE with torchsde?

HardworkingPearl opened this issue · 1 comments

Is it feasible to set diffusion function "g(x)=0" to implement neural ode with torchsde?

In principle, yes. But you won't get to use the high-order solvers tailored for ODEs. You might be better off using something like this if you're trying to do an ODE-based project with torch.