I need to work with individual Wiener increments from an SDE solution in my loss function. Whenever I try to get these values from sol.W.W command, the ERROR: type Nothing has no field W pops up when computing the gradients. Can it be a bug in DiffEqSensitivity package? MWE: using DifferentialEqua…

I think the problem traces back to sol.W being nothing in the backward pass. Using ForwardDiff instead of Zygote to compute the gradients @time gs = ForwardDiff.gradient(p) do p some_loss(p) end removes the error. If reverse-mode AD is needed, you could use pre-defined noise values and NoiseGrid …

Using the noise parameters sol.W.W from an SDE solution throws an error when taking gradients

Specific Domains Machine Learning

MikeKlocCZ October 7, 2020, 2:13pm 4

Thank you both for comments and suggestions!

Topic		Replies	Views
Gradients from an SDE solver with callbacks Machine Learning question , sde	2	517	September 11, 2020
Sensitivity analysis on Non-diagonal noise SDEs Modelling & Simulations diffeq , sde , sciml	1	359	August 31, 2021
ForwardDiffSensitivity() and TrackerAdjoint() give different answers Machine Learning diffeq , sde	3	810	July 18, 2020
Correct sensealg for an ensemble problem of stochastic UODEs with diagonal noise Machine Learning diffeq , flux	17	982	November 23, 2020
Problems using BacksolveAdjoint for an SDE with DiffEqFlux Machine Learning sde	5	721	September 29, 2021

Using the noise parameters sol.W.W from an SDE solution throws an error when taking gradients

Related topics