I’m modeling a PDE for wildfire spread and want to use PyMC to recover parameters. I’m using a custom likelihood function that finds the Intersection Over Union metric comparing the predicted and observed burned areas. I want to use map these metrics to a Beta(5,1) distribution and use that as a lik…

How to troubleshoot sampling error with custom, not differentiable likelihood?

jessegrabowski October 20, 2022, 5:33pm 11

Ah I see. @aseyboldt do you know of any PDE solvers for v4?

Topic		Replies	Views
Sampling crashes with "The derivative of RV [whatever] is zero" when using a custom likelihood defined with pm.Potential Questions	4	4028	February 23, 2019
Defining a numeric (custom) likelihood function in PyMC3 Questions theano	2	3070	August 25, 2018
How to set up a custom likelihood function for two variables Questions	8	13306	March 9, 2018
Averaging over model output that sometimes returns null values? Questions	12	1458	November 16, 2017
PyMC3-Sampling not taking place for the entire range of values between the given bounds of a Uniform prior Questions	7	1606	January 14, 2018