{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreickjqu3smkstuy6yesqpt4575ljqzqmwxockkru5owkx7yiuw5uya",
"uri": "at://did:plc:4rgrdigiftglskeax4wvmsev/app.bsky.feed.post/3mls3tfh3red2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiflo6xt7is6b2iafwghkjahlgggocme5jwjsbeuqqwcywuvjhmszm"
},
"mimeType": "image/png",
"size": 24783
},
"path": "/abs/2605.13806v1",
"publishedAt": "2026-05-14T00:00:00.000Z",
"site": "https://arxiv.org",
"tags": [
"Martino Bernasconi",
"Matteo Castiglioni",
"Andrea Celli",
"Alexandros Hollender"
],
"textContent": "**Authors:** Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Alexandros Hollender\n\nWe study the query complexity of min-max optimization of a nonconvex-nonconcave function $f$ over $[0,1]^d \\times [0,1]^d$. We show that, given oracle access to $f$ and to its gradient $\\nabla f$, any algorithm that finds an $\\varepsilon$-approximate stationary point must make a number of queries that is exponential in $1/\\varepsilon$ or $d$.",
"title": "Min-Max Optimization Requires Exponentially Many Queries"
}