{
  "abstract": "Classical Inverse Optimal Transport (IOT) typically infers a cost function from a single observed transport plan, which may be sensitive to noise and observational biases in practice. To address this limitation, we propose the Multi-Observation Inverse Optimal Transport (M-IOT) framework, which learns a universal cost function from multiple transport plans. We reformulate the resulting bilevel optimization problem into a tractable single-level convex program and characterize the existence and geometric structure of the optimal solution set. Moreover, we propose a Block Coordinate Descent with Anderson-type Extrapolation (BCDwAE) algorithm and establish its Q-linear convergence. Extensive experiments on synthetic data, urban mobility flows, and e-commerce recommendations demonstrate that M-IOT reduces recovery error compared to single-observation baselines and extracts robust structural patterns from noisy multi-view data.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.37291",
  "author_total": 3,
  "authors": [
    {
      "name": "Chenglong Bao"
    },
    {
      "name": "Zanyu Li"
    },
    {
      "name": "Defeng Sun"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0b01jp0cb5cq9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.37291",
  "fulltext_url": null,
  "id": "0b01jp0cb5cq9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.37291",
  "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",
      "math.OC"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.37291",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0b01jp0cb5cq9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:35Z",
      "native_id": "2609.37291",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.37291"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Learning Universal Costs via Multi-Observation Inverse Optimal Transport",
  "title_text": "Learning Universal Costs via Multi-Observation Inverse Optimal Transport",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:35Z",
  "url": "https://research.draconitic.com/paper/0b01jp0cb5cq9",
  "venue": "arXiv",
  "versions": []
}