https://hackerpaper.kaipfister.de/p/1406.5549/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=23536878urn:hackerpapers:mention:1406.5549:23536878Tue, 16 Jun 2020 07:54:21 GMT<p>Wow, that G-GLN paper is really new. Thanks for sharing it :) My first impression is that this will be very challenging to use for many of the people currently using AI in practice, because of the requirement to have a convex and gaussian-distributed result. For example, I currently work on optical flow and the loss functions are usually very jumpy and usually only convex within a few pixels around the correct result. I have seen plenty of modeling errors in optical flow SOTA papers, for example casting a boolean occlusion term so that it can be added to the loss (Won&#x27;t work, no gradient). I…</p><p><a href="https://hackerpaper.kaipfister.de/p/1406.5549/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV