按年被提到
20242024 · 1 次2026
机器学习与深度学习›优化与可微编程·arXiv:2403.14606 · cs.LG

The Elements of Differentiable Programming

Mathieu Blondel, Vincent Roulet · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-03-22 · 最近 2026-07-08
2不同的人
2活跃月份
2讨论串
29被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of differentiable programming. This new programming paradigm enables end-to-end differentiation of complex computer programs (including those with control flows and data structures), making gradient-based optimization of program parameters possible. As an emerging paradigm, differentiable programming builds upon several areas of computer science and applied mathematics, including automatic differentiation, graphical models, optimization and statistics. This book presents a comprehensive review of the fundamental concepts useful for differentiable programming. We adopt two main perspectives, that of optimization and that of probability, with clear analogies between the two. Differentiable programming is not merely the differentiation of programs, but also the thoughtful design of programs intended for differentiation. By making programs differentiable, we inherently introduce probability distributions over their execution, providing a means to quantify the uncertainty associated with program outputs.

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mswphd · 2026-07

“note that similar concepts appear in mathematics. Generally the term for it is a "mollified" function. applied to the step function, you would get a smooth cutoff function https://en.wikipedia.org/wiki/Mollifier#Smooth_cutoff_functions this is also related somewhat to the notion of differentiable programming. RELU is (roughly) the same as x * step(x). …”

NoiseLang: Where N = 5 is a Dirac delta原评论 ↗
被提交为 story · 1 次