Skip to main navigation Skip to search Skip to main content

Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods

  • Fabian Akkerman
  • , Julien Ferry
  • , Christian Artigues
  • , Emmanuel Hebrard
  • , Thibaut Vidal

Research output: Working paperPreprintAcademic

9 Downloads (Pure)

Abstract

Despite their theoretical appeal, totally corrective boosting methods based on linear programming have received limited empirical attention. In this paper, we conduct the first large-scale experimental study of six LP-based boosting formulations, including two novel methods, NM-Boost and QRLP-Boost, across 20 diverse datasets. We evaluate the use of both heuristic and optimal base learners within these formulations, and analyze not only accuracy, but also ensemble sparsity, margin distribution, anytime performance, and hyperparameter sensitivity. We show that totally corrective methods can outperform or match state-of-the-art heuristics like XGBoost and LightGBM when using shallow trees, while producing significantly sparser ensembles. We further show that these methods can thin pre-trained ensembles without sacrificing performance, and we highlight both the strengths and limitations of using optimal decision trees in this context.
Original languageEnglish
PublisherArXiv.org
Number of pages43
DOIs
Publication statusPublished - 24 Jul 2025

Keywords

  • cs.LG

Fingerprint

Dive into the research topics of 'Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods'. Together they form a unique fingerprint.
  • Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods

    Akkerman, F., Ferry, J., Artigues, C., Hébrard, E. & Vidal, T., 2025, In: Transactions on Machine Learning Research. 2025, October, p. 1-43 43 p.

    Research output: Contribution to journalArticleAcademicpeer-review

    Open Access
    File

Cite this