The continuous Bernoulli: fixing a pervasive error in variational autoencoders · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1907.06845/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTThe continuous Bernoulli: fixing a pervasive error in variational autoencoders — mentioned by alentisthttps://news.ycombinator.com/item?id=25240757urn:hackerpapers:mention:1907.06845:25240757Sat, 28 Nov 2020 21:34:26 GMT<p>&gt; I see it’s equivalent to a Beta distribution. It&#x27;s not. The beta distribution is p(x) ∝ x^(α-1) (1-x)^(β-1). x is in the bases. The continuous Bernoulli distribution is p(x) ∝ λ^x (1-λ)^x. x is in the exponents. As https://arxiv.org/abs/1907.06845 says: &gt; the continuous Bernoulli is not a beta distribution (the main difference between these two distributions is how they concentrate mass around the extrema, see appendix 1 for details) The appendix is available here (under &quot;Supplemental&quot;): https://papers.nips.cc/paper/2019/hash/f82798ec8909d23e55679...</p><p><a href="https://hackerpaper.kaipfister.de/p/1907.06845/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.MLThe continuous Bernoulli: fixing a pervasive error in variational autoencoders — mentioned by sdenton4https://news.ycombinator.com/item?id=25235878urn:hackerpapers:mention:1907.06845:25235878Sat, 28 Nov 2020 07:03:19 GMT<p>Looks like this paper gives some background: https://arxiv.org/abs/1907.06845 I&#x27;ve dabbled in VAEs, but haven&#x27;t read this paper. Anyone want to try an ELI5thYearGradStudent?</p><p><a href="https://hackerpaper.kaipfister.de/p/1907.06845/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML