On the Variance of Neural Network Training with respect to Test Sets and Distributions · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2304.01910/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTOn the Variance of Neural Network Training with respect to Test Sets and Distributions — HN submissionhttps://news.ycombinator.com/item?id=35565841urn:hackerpapers:submission:2304.01910:35565841Fri, 14 Apr 2023 05:30:50 GMT<p>Variance Between Runs of Neural Network Training Is Harmless and Inevitable</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2304.01910/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG