pith:D2KERVFX
Graph Signal Diffusion Models for Wireless Resource Allocation
A diffusion model trained on expert allocations can sample near-optimal power controls for graph-structured wireless networks.
arxiv:2604.05175 v2 · 2026-04-06 · eess.SP · cs.IT · cs.LG · math.IT
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{D2KERVFX5EPO76UDIHYU2LDWEP}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
In a power-control case study, we show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates, with strong generalization and transferability across network states.
That the primal-dual expert algorithm produces representative samples from the true conditional distributions over allocations and that time-sharing of diffusion samples is sufficient to achieve ergodic performance without violating constraints.
A graph-conditioned diffusion model learns to sample near-optimal wireless resource allocations by matching distributions from an expert primal-dual algorithm.
Formal links
Cited by
Receipt and verification
| First computed | 2026-07-30T00:08:14.041255Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | unsigned_v0 |
| Schema | pith-number/v1.0 |
Canonical hash
1e9448d4b7e91eeffa8341f14d2c7623e57f4b3e86aff5f7a174781273d9631d
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/D2KERVFX5EPO76UDIHYU2LDWEP \
| 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: 1e9448d4b7e91eeffa8341f14d2c7623e57f4b3e86aff5f7a174781273d9631d
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "9a1833ebad478d5cbc2de126f06fe0a330d3168cbf2ab42452aeef4af3243918",
"cross_cats_sorted": [
"cs.IT",
"cs.LG",
"math.IT"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "eess.SP",
"submitted_at": "2026-04-06T21:12:25Z",
"title_canon_sha256": "f7dc7b60f4c2791cb8bd74d41df134dc63a30eb74477e91fba56e90b6cd3c4bc"
},
"schema_version": "1.0",
"source": {
"id": "2604.05175",
"kind": "arxiv",
"version": 2
}
}