Metraipolis › archive › dc_95684bbfc0d9

Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy — arXiv:2611.01903

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01903
License (as archived)
CC0-1.0
Archived
2026-11-03T18:42:35.651Z
SHA-256 of the archived text
63adc7a5efd029be643fdad0d88cfefd4125b0ad9cdb98035a1264ff3069a150
Stable URL of this page
https://metraipolis.com/documento/dc_95684bbfc0d9

How to cite

Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy — arXiv:2611.01903 — arXiv (en), https://arxiv.org/abs/2611.01903 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95684bbfc0d9 (Metraipolis archive dc_95684bbfc0d9, sha256 63adc7a5efd029be643fdad0d88cfefd4125b0ad9cdb98035a1264ff3069a150)
BibTeX
@misc{dc95684bbfc0d9,
  title = {Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy — arXiv:2611.01903},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01903},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95684bbfc0d9; sha256 63adc7a5efd029be643fdad0d88cfefd4125b0ad9cdb98035a1264ff3069a150},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01903. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tensor factor models provide low-dimensional representations of tensor-valued observations while preserving their multiway structure. When these observations are held by different clients, privacy constraints may prevent them from being pooled for centralized analysis. We study estimation of common loading spaces in Tucker tensor factor models under federated differential privacy, allowing heterogeneous sample sizes, privacy budgets, and factor strengths. The proposed method combines private stability testing, Huber aggregation, and Gaussian perturbation at each client with weighted aggregation at the server. We establish non-asymptotic upper bounds governed by a scaled harmonic mean of the squared local error rates, and prove minimax optimality up to logarithmic factors under strong factors, fixed factor ranks, and fixed noise variance. We further develop a private calibration procedure that selects the local tuning parameters and aggregation weights without knowledge of the noise level or client-specific factor strengths. The resulting adaptive estimator preserves the privacy guarantee and attains the error rate obtained with oracle tuning. We illustrate the finite-sample performance of the proposed estimators through simulation experiments and an application to a Meditation Traits EEG dataset.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Information Theory (cs.IT); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.01903 — 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 2026-11-03T18:13:37.694Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).