Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1706.10239/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTowards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes — mentioned by ogriselhttps://news.ycombinator.com/item?id=32136086urn:hackerpapers:mention:1706.10239:32136086Mon, 18 Jul 2022 09:02:20 GMT<p>There is also this very interesting 2017 paper: Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes Lei Wu, Zhanxing Zhu, Weinan E https://arxiv.org/abs/1706.10239 I think it was the first paper to study the volume of the basins of attraction of good global minima and used the poisoning scheme to highlight the frequency of bad global minima that are typically not reachable found via SGD on the original dataset without poisoning.</p><p><a href="https://hackerpaper.kaipfister.de/p/1706.10239/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG