Densities of almost-surely terminating probabilistic programs are differentiable almost everywhere

by   Carol Mak, et al.

We study the differential properties of higher-order statistical probabilistic programs with recursion and conditioning. Our starting point is an open problem posed by Hongseok Yang: what class of statistical probabilistic programs have densities that are differentiable almost everywhere? To formalise the problem, we consider Statistical PCF (SPCF), an extension of call-by-value PCF with real numbers, and constructs for sampling and conditioning. We give SPCF a sampling-style operational semantics a la Borgstrom et al., and study the associated weight (commonly referred to as the density) function and value function on the set of possible execution traces. Our main result is that almost-surely terminating SPCF programs, generated from a set of primitive functions (e.g. the set of analytic functions) satisfying mild closure properties, have weight and value functions that are almost-everywhere differentiable. We use a stochastic form of symbolic execution to reason about almost-everywhere differentiability. A by-product of this work is that almost-surely terminating deterministic (S)PCF programs with real parameters denote functions that are almost-everywhere differentiable. Our result is of practical interest, as almost-everywhere differentiability of the density function is required to hold for the correctness of major gradient-based inference algorithms.


page 1

page 2

page 3

page 4


ωPAP Spaces: Reasoning Denotationally About Higher-Order, Recursive Probabilistic and Differentiable Programs

We introduce a new setting, the category of ωPAP spaces, for reasoning d...

Towards Denotational Semantics of AD for Higher-Order, Recursive, Probabilistic Languages

Automatic differentiation (AD) aims to compute derivatives of user-defin...

Universal Semantics for the Stochastic Lambda-Calculus

We define sound and adequate denotational and operational semantics for ...

Probabilistic Programs with Stochastic Conditioning

We tackle the problem of conditioning probabilistic programs on distribu...

dPASP: A Comprehensive Differentiable Probabilistic Answer Set Programming Environment For Neurosymbolic Learning and Reasoning

We present dPASP, a novel declarative probabilistic logic programming fr...

String Diagrams with Factorized Densities

A growing body of research on probabilistic programs and causal models h...

A simulated annealing procedure based on the ABC Shadow algorithm for statistical inference of point processes

Recently a new algorithm for sampling posteriors of unnormalised probabi...

Please sign up or login with your details

Forgot password? Click here to reset