按年被提到
20152019 · 1 次2026
机器学习与深度学习›优化与可微编程·arXiv:1502.05767 · cs.SC

Automatic differentiation in machine learning: a survey

Atilim Gunes Baydin, Barak A. Pearlmutter, Alexey Andreyevich Radul, Jeffrey Mark Siskind · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-09-01 · 最近 2020-11-07
2不同的人
2活跃月份
2讨论串
822被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of numeric functions expressed as computer programs. AD is a small but established field with applications in areas including computational fluid dynamics, atmospheric sciences, and engineering design optimization. Until very recently, the fields of machine learning and AD have largely been unaware of each other and, in some cases, have independently discovered each other's results. Despite its relevance, general-purpose AD has been missing from the machine learning toolbox, a situation slowly changing with its ongoing adoption under the names "dynamic computational graphs" and "differentiable programming". We survey the intersection of AD and machine learning, cover applications where AD has direct relevance, and address the main implementation techniques. By precisely defining the main differentiation techniques and their interrelationships, we aim to bring clarity to the usage of the terms "autodiff", "automatic differentiation", and "symbolic differentiation" as these are encountered more and more in machine learning settings.

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ctchocula · 2020-11

“I enjoy reading this author's articles such as the one explaining auto-differentiation [1]. Before that, I tried to understand this survey on auto-differentiation [2], and it just didn't click for me. The analogy to imaginary numbers was perfect. [1] https://blog.demofox.org/2014/12/30/dual-numbers-automatic-differentiation/ [2] https://arxiv.org/abs/15…”

Frequency Domain Image Compression and Filtering原评论 ↗
被提交为 story · 1 次