Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1905.09997/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPainless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates — mentioned by theszhttps://news.ycombinator.com/item?id=48960996urn:hackerpapers:mention:1905.09997:48960996Sat, 18 Jul 2026 18:50:48 GMT<p>ADAM does not work on simple convex problems [1]. [1] https://parameterfree.com/2020/12/06/neural-network-maybe-evolved-to-make-adam-the-best-optimizer/ [2] https://arxiv.org/pdf/1905.09997 [1] refers to [2], which shows that ADAM is not as efficient as gradient descent with line search on some problems, including neural networks.</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.09997/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG