https://hackerpaper.kaipfister.de/p/1805.11284/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=18216828urn:hackerpapers:mention:1805.11284:18216828Mon, 15 Oct 2018 01:42:36 GMT<p>KL divergence is motivated nicely from an information/coding theory viewpoint. It&#x27;s very closely related to Shannon-von Neumann entropy [1], and KL(P||Q) characterizes the efficiency of a code designed for a model distribution P, when applied to reality which is actually represented by Q. A lot of recent work focuses on the Wasserstein divergence [1] as an alternative. One advantage of Wasserstein over KL is that the Wasserstein metric provides better fit over the whole distribution instead of localizing on some specific regions, thereby preventing &quot;mode collapse&quot;. This makes it a popular…</p><p><a href="https://hackerpaper.kaipfister.de/p/1805.11284/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML