{
  "abstract": "We study Lasso estimation for high-dimensional softmax-gated Gaussian mixture-of-experts (SGMoE) regression models, where the predictor dimension P may exceed the sample size N . Under bounded parameters, we establish a non-asymptotic Kullback–Leibler (KL) oracle inequality with an explicit sufficient regularization level and explicit dependence on N , P , response dimension Q , number of experts K , and boundedness constants. We derive sparse well-specified and approximation-space rates, showing how deterministic SGMoE approximation error transfers into statistical KL-risk bounds. The theory extends to random covariates and, under misspecification, controls the best Gaussian SGMoE approximation in the candidate class. Reproducible experiments validate KL decay and density recovery, compare Lasso with SCAD when $$P>N$$ P > N , evaluate model-selection criteria, handle multivariate covariance structures, and assess high-dimensional biological benchmarks relevant to heterogeneous genotype–phenotype mapping, omics-to-trait prediction, and AI-enabled virtual-cell modelling in systems biology.",
  "abstract_shown": true,
  "affiliations": [
    "ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems, School of Mathematical Sciences, Queensland University of Technology, GPO Box 2434, Brisbane, QLD, 4001, Australia",
    "Department of Mathematical and Physical Sciences, School of Computing, Engineering, and Mathematical Sciences, La Trobe University, Bundoora, VIC, 3086, Australia",
    "Institute of Mathematics for Industry, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, 819-0395, Japan",
    "IRT SystemX, 2 Boulevard Thomas Gobert, 91120, Palaiseau, France",
    "School of Mathematics and Physics, The University of Queensland, St Lucia, Brisbane, QLD, 4072, Australia"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "TrungTin Nguyen",
      "orcid": "0000-0001-8433-5980"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Hien D. Nguyen",
      "orcid": "0000-0002-9958-432X"
    },
    {
      "affs": [
        3
      ],
      "name": "Faïcel Chamroukhi",
      "orcid": "0000-0002-5894-3103"
    },
    {
      "affs": [
        4
      ],
      "name": "Geoffrey John McLachlan",
      "orcid": "0000-0002-5921-3145"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7jrm8rekmdmj2.bib",
  "cited_by": 7,
  "doi": "10.1007/s10463-026-01007-5",
  "fulltext_url": null,
  "id": "7jrm8rekmdmj2",
  "issns": [
    "0020-3157",
    "1572-9052"
  ],
  "landing_url": "https://doi.org/10.1007/s10463-026-01007-5",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2613|Statistical Methods and Inference"
    ]
  ],
  "openalex": "W4296563174",
  "pdf_url": "https://link.springer.com/content/pdf/10.1007/s10463-026-01007-5.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": "Springer Science+Business Media",
  "ris": "https://research.draconitic.com/paper/7jrm8rekmdmj2.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T13:20:40Z",
      "native_id": "W4296563174",
      "source": "openalex",
      "url": "https://doi.org/10.1007/s10463-026-01007-5"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "openalex:2613|Statistical Methods and Inference",
      "subfield": "statistics"
    }
  ],
  "title": "Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts",
  "title_text": "Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T13:20:22Z",
  "url": "https://research.draconitic.com/paper/7jrm8rekmdmj2",
  "venue": "Annals of the Institute of Statistical Mathematics",
  "versions": []
}