Metraipolis › archive › dc_532a7dc52ecd
A Unified Framework for Training-Dataset Aggregation and Exact Machine Unlearning via Gibbs Probability Measures — arXiv:2611.05544
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05544
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:22:31.671Z
- SHA-256 of the archived text
99a370ed917355bc0409589b1402ed07b3b3bb35aa2fea8a22a025225953ef4e- Stable URL of this page
https://metraipolis.com/documento/dc_532a7dc52ecd
How to cite
A Unified Framework for Training-Dataset Aggregation and Exact Machine Unlearning via Gibbs Probability Measures — arXiv:2611.05544 — arXiv (en), https://arxiv.org/abs/2611.05544 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_532a7dc52ecd (Metraipolis archive dc_532a7dc52ecd, sha256 99a370ed917355bc0409589b1402ed07b3b3bb35aa2fea8a22a025225953ef4e)
BibTeX
@misc{dc532a7dc52ecd,
title = {A Unified Framework for Training-Dataset Aggregation and Exact Machine Unlearning via Gibbs Probability Measures — arXiv:2611.05544},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05544},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_532a7dc52ecd; sha256 99a370ed917355bc0409589b1402ed07b3b3bb35aa2fea8a22a025225953ef4e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05544. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, three operations on Gibbs probability measures are studied: renormalization, normalized log-linear combination, and nesting. The resulting measures are shown to be Gibbs probability measures with explicit expressions for their objective functions, reference measures, and regularization factors. These measures are further characterized as unique solutions to optimization problems involving linear combinations of the original objective functions, subject to either relative entropy regularization or relative entropy constraints. When the reference measures are probability measures, geometric interpretations of these three operations are established involving Pythagorean identities and exponential geodesics.A central result is the equivalence between nesting and normalized log-linear combinations of Gibbs probability measures. These results are then applied to supervised machine learning with Gibbs algorithms, which are represented by Gibbs probability measures. In this context, either through nesting or log-linear combinations, Gibbs algorithms trained on local datasets are used to form new Gibbs algorithms trained upon the aggregation of all local training datasets. Interestingly, the parameters of such operations, determine the weights of each training data point on the aggregated dataset. %Operations on local Gibbs probability measures are shown to control the contributions of training data. This observation is leveraged for achieving: (a) exact machine unlearning in centralized, decentralized, and federated learning systems; and (b) centralized-equivalent performance, in the sense of producing algorithms trained on the aggregation of all local datasets in decentralized and federated learning . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Information Theory (cs.IT); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05544 — 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 2026-11-05T18:15:49.029Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).