pith:LBYHKZIF
Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
Row-stochastic matrices can converge faster than doubly stochastic matrices in decentralized learning by avoiding extra consensus penalties in weighted geometry.
arxiv:2511.19513 v3 · 2025-11-24 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LBYHKZIFBC3NFDMIJCWCR3OEE7}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
In this geometry, the row-stochastic matrix becomes self-adjoint whereas the doubly stochastic one does not, creating additional penalty terms that amplify consensus error, thereby slowing convergence. We then derive sufficient conditions under which the row-stochastic design converges faster even with a smaller spectral gap.
That the weighted Hilbert-space framework L^2(λ; ℝ^d) is the appropriate geometry for revealing the true convergence behavior and that the identified penalty terms are the dominant differentiator rather than other unmodeled dynamics in the optimization process.
Row-stochastic matrices can provably outperform doubly stochastic matrices in convergence speed for weighted decentralized learning by becoming self-adjoint in a custom L^2(λ; ℝ^d) geometry, eliminating penalty terms that slow consensus.
Formal links
Receipt and verification
| First computed | 2026-06-01T01:02:26.012014Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
587075650508b6d28d8848ac28edc427d22e74088bdea84fb06de791e033ab91
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LBYHKZIFBC3NFDMIJCWCR3OEE7 \
| 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: 587075650508b6d28d8848ac28edc427d22e74088bdea84fb06de791e033ab91
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e954eb4601c01dbdbba7a830b24a85367764ce34a926bf558bab17547e27c15a",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-11-24T02:58:38Z",
"title_canon_sha256": "7f36bbc78e23d25b3faf514c734e5938d7fc62e19cdf81b459838812fc9819ca"
},
"schema_version": "1.0",
"source": {
"id": "2511.19513",
"kind": "arxiv",
"version": 3
}
}