https://hackerpaper.kaipfister.de/p/2401.08281/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=39030583urn:hackerpapers:mention:2401.08281:39030583Wed, 17 Jan 2024 17:19:15 GMT<p>All approximate k-NN algorithms involve tradeoffs, with the main tradeoffs being usually fidelity (recall, vector reconstruction error, end-to-end application error with respect to some metric etc), speed (to query, in either serial or batch mode), and memory usage (vector compression, indexing overhead, etc). There is no one algorithm which is &quot;better&quot; than others along all dimensions; instead, for a given setting you look and see which technique (or combination of techniques) would let you lie along the Pareto-optimal tradeoff curve between fidelity/speed/memory, and for the application…</p><p><a href="https://hackerpaper.kaipfister.de/p/2401.08281/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG