Stability-Based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning
Abstract
Pairwise learning includes various machine learning tasks, with ranking and metric learning serving as the primary representatives. While randomized coordinate descent (RCD) is popular in various problems, there is much less theoretical analysis on the generalization behavior of models trained by RCD, especially under the pairwise learning framework. In this paper, we consider the generalization of RCD for pairwise learning. We measure the on-average argument stability for both convex and strongly convex objective functions, based on which we develop generalization bounds in expectation. The early-stopping strategy is adopted to quantify the balance between estimation and optimization. Our analysis further incorporates the low-noise setting into the excess risk bounds to achieve the optimistic bound as O(1/n), where n is the sample size.
Cite
Text
Wu et al. "Stability-Based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I20.35457Markdown
[Wu et al. "Stability-Based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/wu2025aaai-stability/) doi:10.1609/AAAI.V39I20.35457BibTeX
@inproceedings{wu2025aaai-stability,
title = {{Stability-Based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning}},
author = {Wu, Liang and Hu, Ruixi and Lei, Yunwen},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {21545-21553},
doi = {10.1609/AAAI.V39I20.35457},
url = {https://mlanthology.org/aaai/2025/wu2025aaai-stability/}
}