dorsal/arxiv
View SchemaQuantum computational gradient estimation
| Authors | David Bulger |
|---|---|
| Categories | |
| ArXiv ID | quant-ph/0507109 |
| URL | https://arxiv.org/abs/quant-ph/0507109 |
Abstract
Classically, determining the gradient of a black-box function f:R^p->R requires p+1 evaluations. Using the quantum Fourier transform, two evaluations suffice. This is based on the approximate local periodicity of exp(2*pi*i*f(x)). It is shown that sufficiently precise machine arithmetic results in gradient estimates of any required accuracy.
{
"annotation_id": "c760d974-0ee9-44f7-9cfb-29599edd5438",
"date_created": "2026-03-02T18:02:17.257000Z",
"date_modified": "2026-03-02T18:02:17.257000Z",
"file_hash": "05e8565947913b9e702ded8d4c2a1ab486c408368112ed853f6c3238f626865e",
"private": false,
"record": {
"abstract": "Classically, determining the gradient of a black-box function f:R^p-\u003eR\nrequires p+1 evaluations. Using the quantum Fourier transform, two evaluations\nsuffice. This is based on the approximate local periodicity of\nexp(2*pi*i*f(x)). It is shown that sufficiently precise machine arithmetic\nresults in gradient estimates of any required accuracy.",
"arxiv_id": "quant-ph/0507109",
"authors": [
"David Bulger"
],
"categories": [
"quant-ph"
],
"title": "Quantum computational gradient estimation",
"url": "https://arxiv.org/abs/quant-ph/0507109"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "84ab7167-65e2-46bf-ad80-3371e27b0d45",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}