Backpropagation in the Simply Typed Lambda-calculus with Linear Negation

by   Alois Brunel, et al.

Backpropagation is a classic automatic differentiation algorithm computing the gradient of functions specified by a certain class of simple, first-order programs, called computational graphs. It is a fundamental tool in several fields, most notably machine learning, where it is the key for efficiently training (deep) neural networks. Recent years have witnessed the quick growth of a research field called differentiable programming, the aim of which is to express computational graphs more synthetically and modularly by resorting to actual programming languages endowed with flow control operators and higher-order combinators, such as map and fold. In this paper, we extend the backpropagation algorithm to a paradigmatic example of such a programming language: we define a compositional program transformation from the simply-typed lambda-calculus to itself augmented with a notion of linear negation, and prove that this computes the gradient of the source program with the same efficiency as first-order backpropagation. The transformation is completely effect-free and thus provides a purely logical understanding of the dynamics of backpropagation.



There are no comments yet.


page 1

page 2

page 3

page 4


Operational calculus on programming spaces

In this paper we develop operational calculus on programming spaces that...

CHAD: Combinatory Homomorphic Automatic Differentiation

We introduce Combinatory Homomorphic Automatic Differentiation (CHAD), a...

Visual Backpropagation

We show how a declarative functional programming specification of backpr...

Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning

The Clarke subdifferential is not suited to tackle nonsmooth deep learni...

On the Soundness of Coroutines with Snapshots

Coroutines are a general control flow construct that can eliminate contr...

Learning Probabilistic Programs Using Backpropagation

Probabilistic modeling enables combining domain knowledge with learning ...

Computation Against a Neighbour

Recent works in contexts like the Internet of Things (IoT) and large-sca...
This week in AI

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