Ideas & society2025 · shared on Hacker News
Optimizing ML training with metagradient descent
Explore Optimizing ML training with metagradient descent, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Yladberg ·
Optimizing ML training with metagradient descent
83 points13 comments