No bad local minima: Data independent training error guarantees for multilayer neural networks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1605.08361/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTNo bad local minima: Data independent training error guarantees for multilayer neural networks — mentioned by vardhanwhttps://news.ycombinator.com/item?id=15943461urn:hackerpapers:mention:1605.08361:15943461Sun, 17 Dec 2017 01:44:55 GMT<p>https://arxiv.org/abs/1605.08361 https://arxiv.org/abs/1704.08045</p><p><a href="https://hackerpaper.kaipfister.de/p/1605.08361/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML