https://hackerpaper.kaipfister.de/p/1608.04493/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=23122731urn:hackerpapers:mention:1608.04493:23122731Sat, 09 May 2020 06:25:13 GMT<p>I find the technique very similar to the one presented in [1] from 2018, and I can&#x27;t seem to find a ref to this paper in theirs. Another interesting and very related paper [2] that they fail to mention also shows improvement in training time (epochs) with dynamic pruning And for the ones who wondered how far this is going back time I suggest you to read this one [3] [1] https://www.nature.com/articles/s41467-018-04316-3 [2] https://arxiv.org/abs/1608.04493 [3] https://papers.nips.cc/paper/323-generalization-by-weight-el...</p><p><a href="https://hackerpaper.kaipfister.de/p/1608.04493/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NEhttps://news.ycombinator.com/item?id=13174396urn:hackerpapers:mention:1608.04493:13174396Wed, 14 Dec 2016 07:16:16 GMT<p>There is also this one https://arxiv.org/abs/1506.02515 which takes pruning a step further to reduce the sparsity. Also this one https://arxiv.org/abs/1608.04493 which makes sure not to kill any neurons which proves to be useful at a later stage in the pruning process.</p><p><a href="https://hackerpaper.kaipfister.de/p/1608.04493/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NE