{
  "abstract": "Training a machine learning (ML) model is an optimization process that typically requires a set of examples with ground-truth labels beforehand. Obtaining these ground truths usually requires laborious human effort and can be costly. The scalability of human labeling becomes a concern when there are a large number of data points that need to be labeled. To address this practical issue, we consider an optimization setting where a subset of samples has ground-truth labels, while the remaining data points were labeled by an ML predictor, which could potentially assign incorrect labels to those points. We propose both first-order and zeroth-order stochastic optimization methods for training on datasets consisting of a mix of true-labeled and ML-labeled samples. We further conduct comprehensive empirical studies from training a linear regression model to fine-tuning a large language model (LLM) to showcase the effectiveness of the proposed algorithms for training with ML-labeled data.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.26790",
  "author_total": 2,
  "authors": [
    {
      "name": "Maria-Eleni Sfyraki"
    },
    {
      "name": "Jun-Kun Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dw3kg0gq5fjz7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.26790",
  "fulltext_url": null,
  "id": "dw3kg0gq5fjz7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.26790",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1702|Stochastic Gradient Optimization Techniques"
    ]
  ],
  "openalex": "W7223016913",
  "pdf_url": "https://arxiv.org/pdf/2610.26790",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dw3kg0gq5fjz7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:31:00Z",
      "native_id": "2610.26790",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.26790"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Training with ML-labeled Data via Stochastic First- and Zeroth-Order Optimization",
  "title_text": "Training with ML-labeled Data via Stochastic First- and Zeroth-Order Optimization",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:47Z",
  "url": "https://research.draconitic.com/paper/dw3kg0gq5fjz7",
  "venue": "arXiv",
  "versions": []
}