“This paper titled "Backpropagation in the Simply Typed Lambda-calculus with Linear Negation" describes how to generalize the backpropagation algorithm used for computational graphs (like in PyTorch or TF) to the simply-typed lambda calculus augmented with a notion of linear negation. By relying on conceptual tools originating from Linear Logic, the autho…”
Backpropagation in the Simply Typed Lambda-calculus with Linear Negation
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 control flow 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.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)- Backpropagation in the Simply Typed Lambda-Calculus with Linear Negation ↗headalgorithm · 2019-10-03 · 3 分
- Extending Backpropagation to Functional Programs ↗groar · 2019-11-10 · 2 分