按年被提到
20182018 · 1 次2026
机器学习与深度学习›优化与可微编程·arXiv:1804.00746 · cs.PL

The simple essence of automatic differentiation

Conal Elliott · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2018-12-04 · 最近 2020-02-17
2不同的人
2活跃月份
2讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Automatic differentiation (AD) in reverse mode (RAD) is a central component of deep learning and other uses of large-scale optimization. Commonly used RAD algorithms such as backpropagation, however, are complex and stateful, hindering deep understanding, improvement, and parallel execution. This paper develops a simple, generalized AD algorithm calculated from a simple, natural specification. The general algorithm is then specialized by varying the representation of derivatives. In particular, applying well-known constructions to a naive representation yields two RAD algorithms that are far simpler than previously known. In contrast to commonly used RAD implementations, the algorithms defined here involve no graphs, tapes, variables, partial derivatives, or mutation. They are inherently parallel-friendly, correct by construction, and usable directly from an existing programming language with no need for new data types or programming style, thanks to use of an AD-agnostic compiler plugin.

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

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论Myrmornis · 2018-12

“> Meanwhile, the idea of ML models fundamentally being differentiable algorithms – often called differentiable programming – has caught on. > We need a language to write differentiable algorithms, and Flux takes Julia to be this language. Recently on HN there was some discussion of this paper by Conal Elliott on automatic differentiation in a pure funct…”

Building a Language and Compiler for Machine Learning原评论 ↗
被提交为 story · 1 次