{
  "abstract": "Large-scale signal processing systems, including aeronautical and aerospace platforms, increasingly rely on tensor operations, whose distributed execution is constrained by communication, memory, and latency bottlenecks. In this paper, we propose a tensor-aware coded computation framework for distributed mode-1 tensor--matrix multiplication that operates directly on tensor subtensors, avoiding explicit unfolding and preserving multi-dimensional structure. For a fixed partitioning configuration, the proposed tensor-PolyDot scheme achieves the same recovery threshold, communication cost, worker-side computation, and memory requirements as conventional matrix-based PolyDot schemes. However, by leveraging multivariate encoding, it replaces high-degree univariate interpolation at the fusion node with structured low-dimensional decoding. This leads to a substantial reduction in decoding complexity and latency, without affecting any other system metric. Additionally, the tensor-based approach improves memory locality and enables parallel decoding across tensor modes, making it well-suited to modern hardware architectures. Numerical results show decoding speedups proportional to the tensor partitioning factor, reaching up to an order-of-magnitude improvement in practical settings. These advantages make the proposed framework particularly relevant to latency-critical aeronautical and aerospace distributed signal processing systems.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.30567",
  "author_total": 2,
  "authors": [
    {
      "name": "Ahmad Tanha"
    },
    {
      "name": "Ali Khalesi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0y56msc7pg57t.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.30567",
  "fulltext_url": null,
  "id": "0y56msc7pg57t",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.30567",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "2605|Tensor decomposition and applications"
    ]
  ],
  "openalex": "W7214649696",
  "pdf_url": "https://arxiv.org/pdf/2609.30567",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0y56msc7pg57t.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:34Z",
      "native_id": "2609.30567",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.30567"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "openalex:2605|Tensor decomposition and applications",
      "subfield": "numerical-analysis"
    }
  ],
  "title": "Low-Latency Coded Tensor--Matrix Multiplication for Distributed Signal Processing Systems",
  "title_text": "Low-Latency Coded Tensor--Matrix Multiplication for Distributed Signal Processing Systems",
  "type": "preprint",
  "updated_at": "2026-11-07T18:20:21Z",
  "url": "https://research.draconitic.com/paper/0y56msc7pg57t",
  "venue": "arXiv",
  "versions": []
}