pith:ZICGYLA2
Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant
A quadratic gradient variant lets enhanced optimizers train logistic regression on encrypted data with plaintext-level performance in four iterations.
arxiv:2201.10838 v18 · 2022-01-26 · cs.CR · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{ZICGYLA2UWRQ2YHZ2C5J7GFFCA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
By incorporating this quadratic gradient, we enhance Nesterov's Accelerated Gradient (NAG), Adaptive Gradient (AdaGrad), and Adam algorithms... achieving comparable performance within only four iterations.
The quadratic gradient can be computed and applied under homomorphic encryption with negligible extra cost while preserving the claimed convergence properties and numerical stability across datasets.
Introduces quadratic gradient to enhance NAG, AdaGrad and Adam for logistic regression, claiming SOTA convergence and comparable encrypted training performance in four iterations.
Cited by
Receipt and verification
| First computed | 2026-06-02T02:04:44.486758Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
ca046c2c1aa5a30d60f9d0ba9f98a51008139ec40fc855d3305c5c63af310086
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/ZICGYLA2UWRQ2YHZ2C5J7GFFCA \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: ca046c2c1aa5a30d60f9d0ba9f98a51008139ec40fc855d3305c5c63af310086
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "8e05f06c6ff4bffd189f844c3ded8f1caf9282e5e402b767cbfed8894024ac6a",
"cross_cats_sorted": [
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CR",
"submitted_at": "2022-01-26T09:44:13Z",
"title_canon_sha256": "1d2632be5ccecc44ef3851a649128ebc5346e884772cfca8155bb4604a68df97"
},
"schema_version": "1.0",
"source": {
"id": "2201.10838",
"kind": "arxiv",
"version": 18
}
}