Metraipolis › archive › dc_773f46badd1d
A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm — arXiv:2608.24210
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24210
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:10.929Z
- SHA-256 of the archived text
55186bb52009227317953e805a004c34e0f91d4857166511c9e4bbc6f2c679a0- Stable URL of this page
https://metraipolis.com/documento/dc_773f46badd1d
How to cite
A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm — arXiv:2608.24210 — arXiv (en), https://arxiv.org/abs/2608.24210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_773f46badd1d (Metraipolis archive dc_773f46badd1d, sha256 55186bb52009227317953e805a004c34e0f91d4857166511c9e4bbc6f2c679a0)
BibTeX
@misc{dc773f46badd1d,
title = {A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm — arXiv:2608.24210},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24210},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_773f46badd1d; sha256 55186bb52009227317953e805a004c34e0f91d4857166511c9e4bbc6f2c679a0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Training neural networks requires balancing the trade-off between fitting the training data and achieving robust performance on unseen inputs. This ability, commonly referred to as generalizability, is determined by the gap between the empirical risk on the training set (``empirical loss'') and the expected risk over the data distribution (``generalization error''). Existing approaches typically estimate the generalization error numerically, requiring gradient descent training and an ``early stopping'' strategy. In this work, we introduce an analytic framework that estimates the optimal time of early stopping without the need for training. Several works in the literature also give such analytical estimations, but they are generally based on random matrix theory and often make assumptions on the distribution of the data or the eigenvalue distribution of the covariance matrix. In contrast, our work is based on Rademacher complexity (RC) without needing such probabilistic assumptions. For both theoretical and numerical reasons, it is more relevant to express RC with the L1- norm rather than with the L2-norm. We focus on the case of linear models and the problem of linear regression. Thanks to the ``linear probing'' method, our results can, however, be successfully applied to nonlinear neural networks, as illustrated in the classification MNIST example. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.24210 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T06:28:52.235Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).