Crash running dopri5 about torchdiffeq HOT 4 OPEN

This underflow error indicates that the system is too stiff for an explicit method to solve. The step size needs to be extremely small in order to satisfy the desired tolerance. If dopri5 can't solve it then adams will have the same problem. If you can get away with it, I'd suggest trying to increase the tolerance parameters first atol and rtol. This introduces more numerical error but easier/faster solves.

Stiffness is still a difficult problem to get around. Try architectures with nicer (analytic) activations function, e.g. softplus, Swish. We also used weight decay to reduce the complexity of the system.

from torchdiffeq.

Thank you for your answer. Is there a way to get information on those internal parameters for fine tuning?

from torchdiffeq.

Hmm you're right. It's not clear from the README.md or docstring.

The basic idea is each adaptive solver can produce an error estimate of the current step, and if the error is greater than some tolerance, then the step is redone with a smaller step size, and this repeats until the error is smaller than the provided tolerance.

The tolerance is calculated as atol + rtol * norm of current state, where the norm being used is the infinity norm (https://github.com/rtqichen/torchdiffeq/blob/master/torchdiffeq/_impl/misc.py#L152).

from torchdiffeq.

Maybe we could specify a minimum value as a parameter so it can try its best but chose that value if needed?

from torchdiffeq.