Learning from gradients of a multivariate function

[albapa]

Is it somehow possible to learn a multivariate function f(x,y) from its partial derivatives (and function observations)? The example only shows this for a f(x) univariate function. I'd be grateful for any suggestions or pointers.

[gpleiss]

Does this tutorial help? https://docs.gpytorch.ai/en/stable/examples/08_Advanced_Usage/Simple_GP_Regression_Derivative_Information_2d.html