Categorical semantics of a simple differential programming language
From MaRDI portal
Publication:5019684
Abstract: With the increased interest in machine learning, and deep learning in particular, the use of automatic differentiation has become more wide-spread in computation. There have been two recent developments to provide the theoretical support for this types of structure. One approach, due to Abadi and Plotkin, provides a simple differential programming language. Another approach is the notion of a reverse differential category. In the present paper we bring these two approaches together. In particular, we show how an extension of reverse derivative categories models Abadi and Plotkin's language, and describe how this categorical model allows one to consider potential improvements to the operational semantics of the language.
Recommendations
- Monoidal reverse differential categories
- Differential categories revisited
- Reverse AD at higher types: pure, principled and denotationally correct
- What is a categorical model of the differential and the resource \(\lambda \)-calculi?
- Categories of Differentiable Polynomial Circuits for Machine Learning
Cites work
- scientific article; zbMATH DE number 3730851 (Why is no real title available?)
- scientific article; zbMATH DE number 3741604 (Why is no real title available?)
- scientific article; zbMATH DE number 6982909 (Why is no real title available?)
- scientific article; zbMATH DE number 872103 (Why is no real title available?)
- scientific article; zbMATH DE number 233974 (Why is no real title available?)
- scientific article; zbMATH DE number 3366846 (Why is no real title available?)
- A lattice-theoretical fixpoint theorem and its applications
- A type-theoretical alternative to ISWIM, CUCH, OWHY
- Boolean and classical restriction categories
- Cartesian differential categories
- Cohesive categories and manifolds
- Deep learning
- Differential bundles and fibrations for tangent categories
- Differential calculus over general base fields and rings.
- Differential categories
- Differential restriction categories
- Differential structure, tangent structure, and SDG
- Elgot algebras (extended abstract)
- LCF considered as a programming language
- On 1-form classifiers∗
- Range categories II: Towards regularity
- Restriction categories III: colimits, partial limits and extensivity
- Restriction categories. I: Categories of partial maps
- The Faà di Bruno construction
- The delay monad and restriction categories
- Timed Sets, Functional Complexity, and Computability
- Total maps of Turing categories
Cited in
(12)- Deterministic Caterpillar Expressions
- Correctness of automatic differentiation via diffeologies and categorical gluing
- Differentiable causal computations via delayed trace
- Categorical foundations of gradient-based learning
- A simply typed \(\lambda\)-calculus of forward automatic differentiation
- Latent fibrations: fibrations for categories of partial maps
- Reverse derivative ascent: a categorical approach to learning Boolean circuits
- Categories of Differentiable Polynomial Circuits for Machine Learning
- Learners' languages
- Monoidal reverse differential categories
- Change actions: models of generalised differentiation
- scientific article; zbMATH DE number 742726 (Why is no real title available?)
This page was built for publication: Categorical semantics of a simple differential programming language
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5019684)
