The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1611.00712/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTThe Concrete Distribution: A Continuous Relaxation of Discrete Random Variables — mentioned by eli_gottliebhttps://news.ycombinator.com/item?id=13123866urn:hackerpapers:mention:1611.00712:13123866Wed, 07 Dec 2016 16:44:16 GMT<p>Yeah, not to be too dismissive or cliched, but these slides come off as if LeCun just now got around to reading some Andy Clark or reading neurosci/cogsci papers by Tenenbaum or Friston. The idea that the human brain has to work via active prediction rather than passive signal processing has been well-established in cogsci and neurosci for a while now. The interesting question, then, is how we make machine-learning systems do prediction well. Probabilistic/generative models have been &quot;wandering in the desert&quot; for a while now because Monte Carlo methods are just so slow, especially for…</p><p><a href="https://hackerpaper.kaipfister.de/p/1611.00712/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG