3 HN users recommended this talk4 months2018–2023score 4.5
Years with an HN recommendation, 2007–2026
Cited as the more accessible companion to the paper, and as the most interesting treatment of AD via compiling to categories.
Conal Elliott presents his paper on automatic differentiation, deriving a simple, generalized AD algorithm from a natural specification. Varying the representation of derivatives yields forward and reverse mode algorithms that avoid the complexity and statefulness of backpropagation.
“There's a talk that Conal gives that makes the paper a bit more accessible” (HN, 2022)
The most interesting thing I've seen on AD is "The simple essence of automatic differentiation" (2018) [1]. See past discussion [2], and talk [3]. I think the main idea is that by compiling to categories and pairing up a function with its derivative, the pair becomes trivially composable in forward mode, and the whole structure is easily converted to reverse mode afterwards. [1]: [link] [2]: [link] [3]: Talk at Microsoft Research: [this video] Other presentations listed here: [link]
Compiling to categories makes forward and reverse mode AD composable
Another paper related to AD was posted last month: The Simple Essence of Automatic Differentiation [0]. Video presentation [1]. I found it pretty awesome, just in case you hadn't seen it. [0]: https//news.ycombinator.com/item?id=18306860 [1]: [this video]
Video presentation of the Simple Essence of AD paper
I'm yet to give reverse mode a second try, but my attempts at forward mode (linked in parent post) were on my own without the paper's help. There's a talk that Conal gives that makes the paper a bit more accessible - [this video] - but only a bit more. I know it'll take effort to wrap my head around the implementation details ... but the paper certainly helped clarify things I was stumbling around about.
Talk that makes the AD paper somewhat more accessible
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
6 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Citations, criticism and jokes