https://hackerpaper.kaipfister.de/p/2112.13896/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=30351927urn:hackerpapers:mention:2112.13896:30351927Tue, 15 Feb 2022 20:08:10 GMT<p>While this is true there is also a lot of interesting research going on that makes model training and adaptation to new tasks much more efficient. For example in meta-learning methods like Model Agnostic Meta-Learning (MAML)[1] you learn a model that learns to initialize weights for another model such that it converges very quickly for a new task. For datasets benchmarking new task adaptation there are Meta-Dataset (MD)[2] for Meta-Learning, and the Visual Task Adaptation Benchmark (VTAB)[3] for Representation Learning. Recently to compare the two approaches VTAB+MD[4] was created. Of course…</p><p><a href="https://hackerpaper.kaipfister.de/p/2112.13896/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=30302469urn:hackerpapers:submission:2112.13896:30302469Fri, 11 Feb 2022 15:25:25 GMT<p>Two sparsities are better than one: Performance of sparse-sparse networks</p><p></p><p>51 points; 7 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2112.13896/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG