EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Techniques for mitigating overfitting in machine learning: a comprehensive review, taxonomy, and practical guide

Alexander Pearson Sheppert

Frontiers in Artificial Intelligence · 24.03.2026 · 9

DOI: 10.3389/frai.2026.1794271 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Frontiers in Artificial Intelligence, online erschienen am 24.03.2026. Verfasst von Alexander Pearson Sheppert. Beteiligte Einrichtung: Capitol Technology University, Laurel, MD, United States. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Overfitting remains a persistent barrier to reliable machine learning, especially in modern overparameterized deep models.

Methods

We conducted a narrative review synthesizing approximately 95 core studies (1943–2026) identified through structured searches of IEEE Xplore, ACM Digital Library, arXiv, Google Scholar, and Semantic Scholar, extracting mechanisms, assumptions, and empirical evidence for prominent methods for mitigating overfitting.

Results

We organize techniques into a unified five-family taxonomy (parameter-, training-, data-, ensemble-, and objective-based) and provide a practical decision framework that maps data regimes, model families, and real-world scenarios to actionable regularization strategies.

Conclusion

Overfitting mitigation benefits from coordinated choices in data, model capacity, optimization, and evaluation. Our taxonomy and decision framework help practitioners select complementary interventions and avoid common pitfalls such as leakage and over-regularization.

Schlagwörter

Stichwörter der Autor:innen

data augmentationdeep learningensemblinggeneralizationmodel selectionnarrative reviewoverfittingregularization

Autor:innen und Institutionen

  • Capitol Technology University, Laurel, MD, United States.
  • Legacy Health, Vancouver, WA, United States.

Zitieren

APA

Sheppert, A. P. (2026). Techniques for mitigating overfitting in machine learning: a comprehensive review, taxonomy, and practical guide. Frontiers in Artificial Intelligence, 9. https://doi.org/10.3389/frai.2026.1794271

Vancouver

Sheppert AP. Techniques for mitigating overfitting in machine learning: a comprehensive review, taxonomy, and practical guide. Frontiers in Artificial Intelligence. 2026;9. doi:10.3389/frai.2026.1794271

BibTeX
@article{Sheppert2026,
  author = {Sheppert, Alexander Pearson},
  title = {Techniques for mitigating overfitting in machine learning: a comprehensive review, taxonomy, and practical guide},
  journal = {Frontiers in Artificial Intelligence},
  year = {2026},
  volume = {9},
  doi = {10.3389/frai.2026.1794271}
}
Kostenlos starten →