Verifying a Minimalist Reverse-Mode AD Library

12/14/2021
by   Paulo Emílio de Vilhena, et al.
0

By exploiting a number of relatively subtle programming language features, including dynamically-allocated mutable state, first-class functions, and effect handlers, reverse-mode automatic differentiation can be implemented as a library. One outstanding question, however, is: with which logical tools can one specify what this code is expected to compute and verify that it behaves as expected? We answer this question by using a modern variant of Separation Logic to specify and verify a minimalist (but concise and elegant) reverse-mode automatic differentiation library. We view this result as an advanced exercise in program verification, with potential future applications to more realistic automatic differentiation systems.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/20/2021

Decomposing reverse-mode automatic differentiation

We decompose reverse-mode automatic differentiation into (forward-mode) ...
09/23/2015

The Stan Math Library: Reverse-Mode Automatic Differentiation in C++

As computational challenges in optimization and statistical inference gr...
10/18/2018

Dynamic Automatic Differentiation of GPU Broadcast Kernels

We show how forward-mode automatic differentiation (AD) can be employed ...
03/10/2020

Differentiate Everything with a Reversible Domain-Specific Language

Traditional machine instruction level reverse mode automatic differentia...
03/27/2018

Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator

Deep learning has seen tremendous success over the past decade in comput...
02/23/2021

Event-Based Automatic Differentiation of OpenMP with OpDiLib

We present the new software OpDiLib, a universal add-on for classical op...
11/10/2016

Binomial Checkpointing for Arbitrary Programs with No User Annotation

Heretofore, automatic checkpointing at procedure-call boundaries, to red...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.