Affiliation:
1. University of Cambridge, UK
2. Microsoft Research, UK
3. Tweag, France
Abstract
In this paper, we give a simple and efficient implementation of reverse-mode automatic differentiation, which both extends easily to higher-order functions, and has run time and memory consumption linear in the run time of the original program. In addition to a formal description of the translation, we also describe an implementation of this algorithm, and prove its correctness by means of a logical relations argument.
Publisher
Association for Computing Machinery (ACM)
Subject
Safety, Risk, Reliability and Quality,Software
Cited by
16 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. A taxonomy of automatic differentiation pitfalls;WIREs Data Mining and Knowledge Discovery;2024-09-02
2. A Tensor Algebra Compiler for Sparse Differentiation;2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO);2024-03-02
3. Efficient CHAD;Proceedings of the ACM on Programming Languages;2024-01-05
4. Forward- or reverse-mode automatic differentiation: What's the difference?;Science of Computer Programming;2024-01
5. SLANG.D: Fast, Modular and Differentiable Shader Programming;ACM Transactions on Graphics;2023-12-05