{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiahj3tyoyb3xivzlg2pvvh5wayo6gyvi7hv2zrxncz52ihw42w54i",
"uri": "at://did:plc:4rgrdigiftglskeax4wvmsev/app.bsky.feed.post/3mfbblzewdo42"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiflo6xt7is6b2iafwghkjahlgggocme5jwjsbeuqqwcywuvjhmszm"
},
"mimeType": "image/png",
"size": 24783
},
"path": "/abs/2602.17577v1",
"publishedAt": "2026-02-20T01:00:00.000Z",
"site": "https://arxiv.org",
"tags": [
"Lunjia Hu",
"Kevin Tian",
"Chutong Yang"
],
"textContent": "**Authors:** Lunjia Hu, Kevin Tian, Chutong Yang\n\nOmniprediction is a learning problem that requires suboptimality bounds for each of a family of losses $\\mathcal{L}$ against a family of comparator predictors $\\mathcal{C}$. We initiate the study of omniprediction in a multiclass setting, where the comparator family $\\mathcal{C}$ may be infinite. Our main result is an extension of the recent binary omniprediction algorithm of [OKK25] to the multiclass setting, with sample complexity (in statistical settings) or regret horizon (in online settings) $\\approx \\varepsilon^{-(k+1)}$, for $\\varepsilon$-omniprediction in a $k$-class prediction problem. En route to proving this result, we design a framework of potential broader interest for solving Blackwell approachability problems where multiple sets must simultaneously be approached via coupled actions.",
"title": "Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction"
}