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.
Why Hacker News points people here: Cited as the more accessible companion to the paper, and as the most interesting treatment of AD via compiling to categories.
“There's a talk that Conal gives that makes the paper a bit more accessible”HN comment, 2022
Compiling to categories makes forward and reverse mode AD composable
Full comment
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
RecommendsinfogulchNov 2018
“I found it pretty awesome, just in case you hadn't seen it.”
Video presentation of the Simple Essence of AD paper
Full comment
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
RecommendsnoblethrasherNov 2019
“He also gave nice presentation on AD”
Elliott's nice presentation on automatic differentiation
Full comment
He also gave nice presentation on AD: this video (surprised that you didn't already mention it, considering the venue ;-))
RecommendssrikuSep 2022
“There's a talk that Conal gives that makes the paper a bit more accessible”
Talk that makes the AD paper somewhat more accessible
Full comment
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.
Cites itbmc7505Oct 2018
“Conal Elliott recently gave a longer talk about it at Microsoft Research”
Longer talk by the author on the award-winning AD paper
Full comment
This paper won a best paper award at ICFP 2018. Conal Elliott recently gave a longer talk about it at Microsoft Research: this video
Jokeeli_gottliebAug 2023Full comment
AD is just a Cartesian lens of Jacobians and total derivatives in the category of smooth functions, what's the problem? this video
