{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiee33c7oa7r3wek4ggmjd4vgwo4gyt34ldoznilb7nk6ssr6iucdq",
"uri": "at://did:plc:3fychdutjjusoqeq24ljch6q/app.bsky.feed.post/3mn7eere77tz2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiflo6xt7is6b2iafwghkjahlgggocme5jwjsbeuqqwcywuvjhmszm"
},
"mimeType": "image/png",
"size": 24783
},
"path": "/abs/2605.31386v1",
"publishedAt": "2026-06-01T00:00:00.000Z",
"site": "https://arxiv.org",
"tags": [
"Jason M. Altschuler",
"Pablo A. Parrilo"
],
"textContent": "**Authors:** Jason M. Altschuler, Pablo A. Parrilo\n\nCan gradient descent be accelerated by just choosing better stepsizes? Surprisingly, the answer is yes. This short expository article provides an accessible introduction to this phenomenon of stepsize hedging.",
"title": "Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent"
}