Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2206.01278/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks — mentioned by nmfisherhttps://news.ycombinator.com/item?id=36136488urn:hackerpapers:mention:2206.01278:36136488Wed, 31 May 2023 09:57:28 GMT<p>Research [0] suggests that pretraining to uncover sparse subnetworks is faster when using &quot;easy&quot; subsets of the training data. Very small part of the overall picture but I do expect to see more research on data hashing/subsetting/ordering for training optimization in the near future. [0] https://arxiv.org/pdf/2206.01278.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/2206.01278/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG