Extending Pathwise Gradients to Discrete Random Variables via Finite-Order Relaxation

Excerpt

arXiv:2610.07786v1 Announce Type: new Abstract: Pathwise gradients are preferred for continuous random variables because they are unbiased, low variance, and work with a single sample. For discrete variables, however, the pathwise identity cannot generally be exact for every differentiable function. We propose a general framework to construct finite-order exact pathwise gradient estimators for a range of common discrete variables such as Poisson. The estimator is the least-norm solution among al