search

rtqichen / torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
MIT License
5.61k stars 930 forks source link

Typo in paper (?) #245

Open p0p4k opened 11 months ago

p0p4k commented 11 months ago

Hello, @rtqichen shouldn't the partial derivative actually be TOTAL derivative? (arxiv NODE paper, page 14)

image

ReHoss commented 5 months ago

@p0p4k , I think you are right, the formula is given for $t \mapsto p \circ (z(t), t)$.