On statistical learning via the lens of compression · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1610.03592/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOn statistical learning via the lens of compression — mentioned by nyrikkihttps://news.ycombinator.com/item?id=39865465urn:hackerpapers:mention:1610.03592:39865465Fri, 29 Mar 2024 15:45:58 GMT<p>PAC learning is compression. PAC learnable, Finite VC dimensionality, and the following form of compression are fully equivalent. https://arxiv.org/abs/1610.03592 Basically each individual neuron/perceptron just splits a space into two subspaces.</p><p><a href="https://hackerpaper.kaipfister.de/p/1610.03592/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG