Anytime Sampling for Autoregressive Models via Ordered Autoencoding · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2102.11495/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTAnytime Sampling for Autoregressive Models via Ordered Autoencoding — mentioned by tonic_sectionhttps://news.ycombinator.com/item?id=26355883urn:hackerpapers:mention:2102.11495:26355883Fri, 05 Mar 2021 12:02:49 GMT<p>You mixed up implicit and explicit models. For anyone interested in the difference - implicit models such as GANs don&#x27;t allow you to evaluate the probability density over datapoints - you can only sample from some surrogate model of the distribution learned by minimizing some &#x27;distance&#x27; between the surrogate and the true empirical distribution. &#x27;Explicit&#x27; models (I think this term is nonstandard) parameterize the density directly and modify the parameters via maximum likelihood. This allows one in theory to both directly evaluate the density and sample from the learned distribution. VAEs…</p><p><a href="https://hackerpaper.kaipfister.de/p/2102.11495/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG