Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy
math.ST, cs.IT, math.IT, stat.ML, stat.TH
Submitted: 2026-11-01
Updated: 2026-11-01
Comments: 70 pages
License: http://creativecommons.org/licenses/by/4.0/
The gist: Tensor factor models provide low-dimensional representations of tensor-valued observations while preserving their multiway structure.
Terminology
Abstract
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.
Sources
- Optimal Federated Learning for Functional Mean Estimation under Heterogeneous Privacy Constraints
- Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints
- A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
- Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
- Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices
- Factor Strength Estimation in Vector and Matrix Time Series Factor Models
- Note on sampling without replacing from a finite collection of matrices
- Robust Statistical Inference for Large-dimensional Matrix-valued Time Series via Iterative Huber Regression
- Optimal Cox regression under federated differential privacy: coefficients and cumulative hazards
- Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm
- Federated Transfer Learning with Differential Privacy
- Optimal estimation in private distributed functional data analysis
- Estimating shared subspace with AJIVE: the power and limitation of multiple data matrices
- Detection and Mode-Identification of Multiple Change Points in Tensor Factor Models
Related papers
- Sigmoid-FTRL: Design-Based Adaptive Neyman Allocation for AIPW Estimators
- Nonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Optimal Linear Functional Estimation for Proportionally High-Dimensional Linear Models
- Semiparametric Efficient Inference under Non-Informative Complex Survey Designs
- Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel