{
  "abstract": "Quantum Reservoir Computing (QRC) uses fixed quantum dynamics as a high-dimensional feature map. Still, standard pipelines flatten reservoir measurements and train a linear readout, ignoring the natural tensor structure across time steps, qubits, and observables. We propose a multilinear readout for quantum reservoir computing (ML-QRC), a tensor-structured neural readout compressed through mode-wise projections. Relative to a dense hidden-width-64 neural readout, this reduces the feature-to-hidden parameter count from $64TnF$ to $d(T+n+F)+64d^3$, giving a $12.1\\times$ feature-block compression at $T=50$, $n=6$, $d=8$, and $F=n+\\binom{n}{2}$. Across Mackey-Glass forecasting and TFIM phase classification, ML-QRC remains statistically competitive with Ridge on Mackey-Glass and obtains the numerically highest full-data TFIM accuracy among tested methods, while using $12.0\\times$ fewer parameters than the full dense MLP. Its clearest benefit is improved low-data stability relative to neural MLP readouts on Mackey-Glass; this advantage does not transfer to TFIM, where Ridge performs best at 50\\% data. Overall, ML-QRC is best viewed as a tensor-structured neural readout that compresses dense MLP readouts while preserving QRC tensor structure, rather than as a replacement for simple linear/Ridge readouts in the tested regime.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.13974",
  "author_total": 2,
  "authors": [
    {
      "name": "Van Tien Nguyen"
    },
    {
      "name": "Panagiotis Markopoulos"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7w83g53ffemvd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.13974",
  "fulltext_url": null,
  "id": "7w83g53ffemvd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.13974",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Neural Networks and Reservoir Computing"
    ]
  ],
  "openalex": "W7221796098",
  "pdf_url": "https://arxiv.org/pdf/2610.13974",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7w83g53ffemvd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:06Z",
      "native_id": "2610.13974",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.13974"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing",
  "title_text": "Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:06Z",
  "url": "https://research.draconitic.com/paper/7w83g53ffemvd",
  "venue": "arXiv",
  "versions": []
}