Metraipolis › archive › dc_5fbd025dea15
Efficient Exact Unlearning for Federated Zeroth-Order Optimization — arXiv:2610.35211
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35211
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:02:34.305Z
- SHA-256 of the archived text
6e150823453945514ef967e03f34ac682f65907eb720ede9393574d5bc473040- Stable URL of this page
https://metraipolis.com/documento/dc_5fbd025dea15
How to cite
Efficient Exact Unlearning for Federated Zeroth-Order Optimization — arXiv:2610.35211 — arXiv (en), https://arxiv.org/abs/2610.35211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fbd025dea15 (Metraipolis archive dc_5fbd025dea15, sha256 6e150823453945514ef967e03f34ac682f65907eb720ede9393574d5bc473040)
BibTeX
@misc{dc5fbd025dea15,
title = {Efficient Exact Unlearning for Federated Zeroth-Order Optimization — arXiv:2610.35211},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35211},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fbd025dea15; sha256 6e150823453945514ef967e03f34ac682f65907eb720ede9393574d5bc473040},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated zeroth-order optimization (FedZOO) reduces the memory and communication costs of collaborative training for edge intelligence by avoiding backpropagation while communicating only random seeds and scalar coefficients. However, existing methods lack efficient mechanisms for exact unlearning to fully remove the influence of training data when users request deletion. A key insight is that total variation stability of the learning algorithm creates overlap between model distributions before and after data deletion, allowing exact unlearning to reuse computation through coupling. Based on this observation, we jointly design two stable zeroth-order learning algorithms and their corresponding exact-unlearning procedures: \textsc{FedZOO-S} obtains stability through client and mini-batch subsampling, enabling \textsc{FedZOUL-S} to perform efficient unlearning by preserving earlier updates and restarting from the first affected step. \textsc{FedZOO-NS} further combines subsampling with Gaussian noise to increase overlap between update distributions; \textsc{FedZOUL-NS} exploits this overlap through rejection--reflection coupling to reuse affected updates when the coupling is accepted. We prove exact unlearning for both algorithms: the model and saved state have the same joint distribution as retraining with the corresponding learner on retained data. We further establish stability and convergence guarantees for the learning algorithms and derive upper bounds on expected unlearning cost. Experiments demonstrate effective unlearning with competitive model utility and up to $56.1\%$ less cumulative unlearning time than re-optimization. Compared with first-order baselines, our methods reduce communication overhead by up to approximately four orders of magnitude.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Networking and Internet Architecture (cs.NI).
Pagina del lavoro: https://arxiv.org/abs/2610.35211 — 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 2026-10-27T07:55:30.972Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).