A General Theory for Training Learning Machine · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1704.06885/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA General Theory for Training Learning Machine — mentioned by phzhqhttps://news.ycombinator.com/item?id=17081346urn:hackerpapers:mention:1704.06885:17081346Wed, 16 May 2018 10:43:32 GMT<p>I&#x27;m the author of this paper. I didn&#x27;t realize this paper cause so many intensively discussions here until I heard from my friends. I really appreciate your advice. I would like to explain some questions about this paper. First, this method is not based on comparsion, I definitely know the lower boundary of comparsion sorting is NlogN. The idea of this algorithm is that when we sort big data, the data may have some statistical properties cause it so large, and if we choose some of them, the sub-dataset should hold the properties, this is the basic assumption. I know this assumption is strong…</p><p><a href="https://hackerpaper.kaipfister.de/p/1704.06885/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML