For a task I need to execute Poisson regression. Up until recently, I figured this was no big deal. However, it’s come to my attention that Gradient computations for discrete RVs / PMFs is limited or not supported. The Gamma PDF does not have the same parameter(s), but it does have continuous shape…

You should have no problem with Poisson regression. Gradients are taken of the Poisson log likelihood with respect to the rate parameter \mu which is continuous, not the discrete count observed data y since the data is fixed.

Use of Gamma PDF for Poisson regression?

Questions

jbuddy_13 December 16, 2020, 8:46pm 5

Ohh!

Topic		Replies	Views
Continuous Distribution Alternative to Poisson to take advantage of NUTS Questions	1	798	January 4, 2018
HMC for discrete parameter estimation using gaussian process regression for gradient info? Questions	0	407	April 9, 2021
Custom discrete distribution for zero truncated Poisson Questions	10	2608	December 19, 2017
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
Biased (?) results from Poisson regression model Questions	4	1192	January 17, 2020

Use of Gamma PDF for Poisson regression?

Related topics