https://hackerpaper.kaipfister.de/p/1905.01067/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=22520218urn:hackerpapers:mention:1905.01067:22520218Sun, 08 Mar 2020 20:03:53 GMT<p>What you are stating is the original Lottery Ticket Hypothesis. What they prove in this paper is the stronger version, empirically noticed here https://arxiv.org/abs/1905.01067 and referred to as &quot;supermasks&quot;. To quote from the paper posted here: &quot;within a sufficiently overparameterized neural network with random weights (e.g. at initialization), there exists a subnetwork that achieves competitive accuracy&quot;. Edit: See also https://arxiv.org/abs/1911.13299</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.01067/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=19942588urn:hackerpapers:mention:1905.01067:19942588Fri, 17 May 2019 19:17:33 GMT<p>Follow up from ICLR really elucidates some of the questions raised by this: https://eng.uber.com/deconstructing-lottery-tickets/ https://arxiv.org/abs/1905.01067</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.01067/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG