You Only Linearize Once: Tangents Transpose to Gradients — mentioned by mattjjatgoogle

Sat, 11 Feb 2023 23:27:12 GMT

I'm sure there's a lot of good material around, but here are some links that are conceptually very close to the linked Autodidax. (Disclaimer: I wrote Autodidax and some of these other materials.) There's Autodidact [0], a predecessor to Autodidax, which was a simplified implementation of the original Autograd [1]. It focuses on reverse-mode autodiff, not building an open-ended transformation system like Autodidax. It's also pretty close to the content in these lecture slides [2] and this talk [3]. But the autodiff in Autodidax is more sophisticated and reflects clearer thinking. In…

Paper and discussion history. A mention is not an endorsement.

You Only Linearize Once: Tangents Transpose to Gradients · HackerPapers discussions

You Only Linearize Once: Tangents Transpose to Gradients — mentioned by mattjjatgoogle