{
  "abstract": "We consider the problem of learning structured linear dynamical systems over convex sets $\\mathcal{K}$, where only a small subset of the observations are available at each time point. An estimator which minimizes a bias-corrected, potentially non-convex objective function is proposed. Non-asymptotic bounds are obtained for the statistical error, which depend on the local complexity of $\\mathcal{K}$, the trajectory length $T$, and the sub-sampling probability $p$. Convergence of the projected gradient descent algorithm is also established. The general theory is applied to settings where (i) $\\mathcal{K}$ is a subspace, (ii) $\\mathcal{K}$ is the set of bi-isotonic matrices, and (iii) $\\mathcal{K}$ is the set of matrices whose rows are formed by sampling Lipschitz functions. We show meaningful recovery of the transition matrix is possible for values of $T$ much smaller than what is required in the unconstrained case, and for $p = o(1)$.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.11869",
  "author_total": 3,
  "authors": [
    {
      "name": "Aravinda Kanchana Ruwanpathirana"
    },
    {
      "name": "Hemant Tyagi"
    },
    {
      "name": "Sunny G. W. Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/akcmpf3chqet0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.11869",
  "fulltext_url": null,
  "id": "akcmpf3chqet0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.11869",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "arxiv",
      "math.ST"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "arxiv",
      "stat.TH"
    ],
    [
      "openalex",
      "2206|Sparse and Compressive Sensing Techniques"
    ]
  ],
  "openalex": "W7221142026",
  "pdf_url": "https://arxiv.org/pdf/2610.11869",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/akcmpf3chqet0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:58Z",
      "native_id": "2610.11869",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.11869"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:math.ST",
      "subfield": "statistics"
    }
  ],
  "title": "Learning structured linear dynamical systems from missing observations",
  "title_text": "Learning structured linear dynamical systems from missing observations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:03Z",
  "url": "https://research.draconitic.com/paper/akcmpf3chqet0",
  "venue": "arXiv",
  "versions": []
}