News for hackers. Stuff that matters.

A comment on Deepmind Alphadev: Faster sorting algorithms discovered using deep RL. Parent comment

Re:Deepmind Alphadev: Faster sorting algorithms discovered u... by gumby on Wednesday June 07, 2023 @02:13PM (#36230923)
Your description makes the approach sound like applying ca 1980s simulated annealing, also a form of gradient descent. Am I missing something?
[ Parent | on HN ]
Re:Deepmind Alphadev: Faster sorting algorithms discovered u... by ska on Wednesday June 07, 2023 @02:40PM (#36231413)
This doesn't really sound like SA, which is a principled approach to avoid the local min problem in descent algorithms and end up with a true global optimization. The general result is clean and impractical, the approximations hard to analyze.
[ Parent | on HN ]