Weighting-Based Strategies for Classification: Analysis and Local Peak Dynamics with CART Trees
Abstract
Tabular learning tasks often suffer from class imbalance, which is often addressed via weighting-based strategies. In this work, we compare the naive approach (unweighted) with the weighting-based rebalancing strategies. Somewhat surprisingly, we demonstrate that, asymptotically, as the predictor complexity increases with sample size, weighting strategies yield predictive performance identical to unweighted approaches across all evaluation metrics, up to a shift in the final threshold. To go beyond, we theoretically study the estimation of a linear regression function through weighted and unweighted CART trees with limited depths. In this setting, we prove that the points in the PR space for both strategies are distributed along the same curve, thus illustrating the similar nonasymptotic performance of the two strategies. Then, we numerically identify more complex synthetic settings where performance gaps, evaluated via fixed classifier complexity, favor weighting strategies. Thus, to guide practitioners, we introduce an indicator that aims at signaling whether a data set may benefit from weighting.
Related
- Optimal Mixing for Local Edge-Coloring Dynamics on Trees
- HARS: LDPC Bit-Flipping Decoding With Initial-Syndrome-Conditioned Parameter Mapping and Local-Reliability Weighting
- Hierarchical Gaussian Processes for Survey Weighting: Local Equivalent Weights in Structured Populations
- The skeleton-blocks decomposition of Bienaymé trees, and applications to their local convergence
- A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees
BibTeX
@misc{sakho2026weightingbased,
title = {{Weighting-Based Strategies for Classification: Analysis and Local Peak Dynamics with CART Trees}},
author = {Abdoulaye Sakho and Emmanuel Malherbe and Erwan Scornet},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.18037},
eprint = {2610.18037},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05795518v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Weighting-Based Strategies for Classification: Analysis and Local Peak Dynamics with CART Trees
AU - Abdoulaye Sakho
AU - Emmanuel Malherbe
AU - Erwan Scornet
PY - 2026
DA - 2026/10/12
PB - HAL
DO - 10.48550/arxiv.2610.18037
UR - https://hal.science/hal-05795518v1
AB - Tabular learning tasks often suffer from class imbalance, which is often addressed via weighting-based strategies. In this work, we compare the naive approach (unweighted) with the weighting-based rebalancing strategies. Somewhat surprisingly, we demonstrate that, asymptotically, as the predictor complexity increases with sample size, weighting strategies yield predictive performance identical to unweighted approaches across all evaluation metrics, up to a shift in the final threshold. To go beyond, we theoretically study the estimation of a linear regression function through weighted and unweighted CART trees with limited depths. In this setting, we prove that the points in the PR space for both strategies are distributed along the same curve, thus illustrating the similar nonasymptotic performance of the two strategies. Then, we numerically identify more complex synthetic settings where performance gaps, evaluated via fixed classifier complexity, favor weighting strategies. Thus, to guide practitioners, we introduce an indicator that aims at signaling whether a data set may benefit from weighting.
ER -