{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibu45kt4e77astdw4edma5n5yqlu5yy4i6rnwufdbozbu4sazwizi",
"uri": "at://did:plc:4rgrdigiftglskeax4wvmsev/app.bsky.feed.post/3mfbblv7acum2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiflo6xt7is6b2iafwghkjahlgggocme5jwjsbeuqqwcywuvjhmszm"
},
"mimeType": "image/png",
"size": 24783
},
"path": "/abs/2602.17488v1",
"publishedAt": "2026-02-20T01:00:00.000Z",
"site": "https://arxiv.org",
"tags": [
"Badih Ghazi",
"Cristóbal Guzmán",
"Pritish Kamath",
"Alexander Knop",
"Ravi Kumar",
"Pasin Manurangsi"
],
"textContent": "**Authors:** Badih Ghazi, Cristóbal Guzmán, Pritish Kamath, Alexander Knop, Ravi Kumar, Pasin Manurangsi\n\nWe study the problem of differentially private (DP) computation of coreset for the $k$-means objective. For a given input set of points, a coreset is another set of points such that the $k$-means objective for any candidate solution is preserved up to a multiplicative $(1 \\pm α)$ factor (and some additive factor). We prove the first computational lower bounds for this problem. Specifically, assuming the existence of one-way functions, we show that no polynomial-time $(ε, 1/n^{ω(1)})$-DP algorithm can compute a coreset for $k$-means in the $\\ell_\\infty$-metric for some constant $α> 0$ (and some constant additive factor), even for $k=3$. For $k$-means in the Euclidean metric, we show a similar result but only for $α= Θ\\left(1/d^2\\right)$, where $d$ is the dimension.",
"title": "Computational Hardness of Private Coreset"
}