Stochastic gradient descent with gradient estimator for categorical features · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2209.03771/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTStochastic gradient descent with gradient estimator for categorical features — mentioned by victorNicollethttps://news.ycombinator.com/item?id=35067001urn:hackerpapers:mention:2209.03771:35067001Wed, 08 Mar 2023 09:36:44 GMT<p>We&#x27;ve been doing this type of gradient descent in production for a couple of years now, and we&#x27;ve been very happy with it. A few insights from my experience: One of the main benefits of doing differentiable programming over a relational database is that you can use joins to traverse the normalized data schema, and this acts as a very effective prior for your model. For example, you can learn parameters associated to shirt colors by having a parameter in the color table, and joining it with the shirt sales table (through the shirts table). And knowledge of the table structure also lets you…</p><p><a href="https://hackerpaper.kaipfister.de/p/2209.03771/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG