betaFeedback

WorksMathematics

Federated Estimation of Loading Spaces in Tensor Factor Models under Differential Privacy

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.

Introduction

Modern applications increasingly generate complex data with multiway structures. Examples include facial images indexed by person, lighting condition, and pixel location [38]; recommendation data indexed by user, item, and context [37]; and gene-expression data indexed by individual mouse, tissue type, and gene [1]. The resulting tensors are often high-dimensional, making it desirable to represent the data parsimoniously while preserving the multiway structure as each tensor mode may exhibit a distinct source of variation. The Tucker tensor factor model provides such a representation through decomposing the data into a low-rank component driven by a core factor tensor, and an idiosyncratic noise, under which it is of interest to learn the low-dimensional spaces spanned by mode-specific loading matrices that describe the main patterns of variation along each mode [20, 18, 3, 6].

In many applications, tensor-valued observations are held by multiple clients, and privacy regulations or institutional restrictions may prevent them from being pooled for centralized analysis; consider e.g., patient imaging data held by hospitals, gene-expression measurements stored by research centers, and user–item data retained by platforms in different jurisdictions. Federated learning allows these clients to collaborate by transmitting locally computed model updates or summary statistics to a central server for aggregation, while retaining the raw observations locally [42]. However, keeping the raw data in local clients does not by itself does not provide a formal privacy guarantee, since transmitted outputs may still reveal information about individual records. Federated differential privacy (FDP) addresses this risk by requiring that any output released by each client to satisfy record-level differential privacy (DP), so that its distribution remains stable under the replacement of any single local record [23, 24].

Despite the growing literature on FDP estimation, methods and statistical theory specific for tensor data are underdeveloped, particularly on the trade-off between privacy and statistical efficiency. We propose to close this gap by studying the problem of estimating mode-wise loading spaces in Tucker tensor factor models under FDP, which comes with worst-case record-level FDP under arbitrary record replacements.

Related literature

Our work lies at the intersection of tensor factor models, differentially private principal component analysis (PCA), and FDP.

Tensor factor models. Low-rank tensor models are commonly formulated through Tucker or canonical polyadic (CP) decompositions [20, 38]. Building on the Tucker decomposition, statistical tensor factor models represent tensor-valued observations through latent core tensors and mode-specific loading matrices. Generalizing from matrix factor models by Wang et al. [50], the seminal work by Chen et al. [18] considered a Tucker-type model for high-dimensional tensor time series. Barigozzi et al. [6] studied a Tucker tensor factor model and developed an iterative projection estimator, deriving convergence rates and asymptotic distributions for the loading matrices and common factors. Babii et al. [3] showed that tensor PCA is rate-optimal under strong factors, while alternating least squares improves the convergence rate under weak factors. More recent literature has seen a wide range of developments (e.g. [19, 30, 16, 5, 56]; see a recent review in Bolivar et al. [8]. All these studies consider tensor factor models without privacy constraints.

Differentially private PCA. PCA provides a low-dimensional representation of multivariate data by identifying orthogonal directions that capture the dominant variation [35, 36] and has popularly been adopted for estimation of factor models and other low-rank structures. Early work on differentially private PCA studied fixed, bounded datasets without making distributional assumptions [7, 17, 25]. Subsequent work considered private PCA in distributed settings under boundedness assumptions. Wang and Xu [51] studied non-interactive locally private PCA and obtained optimal or near-optimal rates in low-dimensional and sparse high-dimensional settings. Grammenos et al. [27] developed a differentially private federated PCA for bounded streaming data under homogeneous sample sizes and privacy budgets. More recent work has considered unbounded observations under distributional assumptions. Liu et al. [41] established nearly optimal rates for rank-one PCA under sub-Gaussian distributions. For general-rank PCA, Cai et al. [14] obtained nearly minimax-optimal rates under the spiked covariance model, but their privacy guarantee holds only with high probability and for independent-copy replacements rather than arbitrary record replacements. Düngler and Sanyal [21] subsequently developed an iterative algorithm for general-rank PCA with worst-case privacy guarantees and established nearly matching upper and lower error bounds. In all above, the focus lies in the study of PCA-based methods for a sequence of random vectors, and their guarantees do not extend to tensor-valued data without careful investigation into the multiarray structure.

Federated differential privacy. This framework requires each client’s complete release to satisfy DP with respect to its local dataset, while the central server has access only to these privatized releases [52] (Li et al. 2024b). FDP has been studied in a range of statistical problems, including mean estimation and linear regression (Li et al., 2024b), nonparametric regression and classification [11, 2], functional data analysis [10, 53], and Cox regression [34]. In these works, minimax framework has been adopted for the quantification of the cost of privacy, establishing minimax lower bounds on the rates of estimation accompanied by matching upper bounds up to logarithmic factors. Minimax-optimal rates have been established in these settings, up to logarithmic factors. Most closely related to our setting, Li et al. (2024a) studied federated estimation of a common principal subspace and covariance matrix under the spiked covariance model. They obtained an upper bound matching the federated minimax lower bound up to logarithmic factors but as in Cai et al. [14], their privacy guarantee is limited in its formulation.

List of contributions

The main contributions of this paper are summarized as follows.

Firstly, we develop a novel loading-space estimator for Tucker tensor factor models under FDP, allowing for heterogeneous sample sizes, privacy budgets, and factor strengths. The proposed algorithm combines a private stability test performed on blockwise loading-space projectors, a Huber loss-based aggregation strategy, and Gaussian perturbations for constructing a private local projector. Then, the central server aggregates these local projectors using client-specific weights. Through these steps, the algorithm guarantees worst-case record-level FDP under arbitrary record replacements, in contrast to existing studies which only provide high probability guarantees and permit independent-copy replacements [14] (Li et al. 2024a). Secondly, we establish the non-asymptotic upper bound for the oracle procedure whose Huber radii, noise scales, and aggregation weights depend on the unknown noise level and client-specific factor strengths. Our results show that these rates are governed by a scaled harmonic mean of the squared local error rates, which is no larger than the smallest squared local error rate and can vanish as the number of clients increases even when none of the local rates does. We derive a federated minimax lower bound with the same harmonic structure, establishing minimax optimality up to logarithmic factors under strong factors with fixed ranks and noise variance. Our upper bound is attained under the same worst-case FDP requirement as the lower bound and, to the best of our knowledge, this is the first minimax-optimality result for low-rank structure estimation for tensor-valued data under the worst-case FDP.

Thirdly, we develop a private calibration procedure that adaptively selects the local tuning parameters and aggregation weights without knowledge of the noise level or client-specific factor strengths. In Li et al. (2024b), clients share a common covariance matrix, so the common signal and noise parameters cancel from the normalized PCA aggregation weights. In our setting, we allow factor strengths to vary across clients, so the optimal weights additionally depend on unknown client-specific signal parameters. In addition, both their procedure and our oracle procedure require knowledge of the noise level and signal strength to calibrate the Gaussian perturbation added for privacy. To address both sources of dependence, each client uses a separate calibration sample and a private threshold search to estimate the dispersion of its blockwise loading-space projectors. The resulting scale estimate determines the Huber radii, the scale of perturbations, and the estimated local error rate used to compute the aggregation weights. Our adaptive estimator retains the same worst-case privacy guarantee and, under the additional signal condition, attains the same error rate as the oracle estimator.

Notation and organization

We use bold uppercase letters (e.g. X\mathbf{X}) for tensors, plain uppercase letters (e.g. AA) for matrices, bold lowercase letters (e.g. x\mathbf{x}) for vectors, and plain lowercase letters (e.g. t,λt,\lambda) for scalars. For any positive integer pp, let [p]={1,…,p}[p]=\{1,\ldots,p\}. For real numbers a,ba,b, write a∨b=max⁡{a,b}a\vee b=\max\{a,b\} and a∧b=min⁡{a,b}a\wedge b=\min\{a,b\}. For a matrix A∈Rp1×p2A\in\mathbb{R}^{p_1\times p_2}, denote by ∥A∥\lVert A\rVert its spectral norm, ∥A∥F\lVert A\rVert_{\mathrm{F}} its Frobenius norm, and λ1(A)≥⋯≥λp1∧p2(A)≥0\lambda_1(A)\geq\cdots\geq\lambda_{p_1\wedge p_2}(A)\geq0 its singular values. For j∈[p1∧p2]j\in[p_1\wedge p_2], let SVD⁡j(A)\operatorname{SVD}_j(A) denote the matrix whose columns are the leading jj left singular vectors of AA; we fix a measurable selection rule whenever there is a tie at the singular values. For symmetric matrices A,BA,B of the same dimension, write A⪯BA\preceq B if B−AB-A is positive semidefinite. For integers p≥rp\geq r, define the Stiefel manifold Op×r={U∈Rp×r:UTU=Ir}\mathbb{O}_{p\times r}=\{U\in\mathbb{R}^{p\times r}:U^{\mathsf{T}}U=I_r\}. For a matrix U∈Op×rU\in\mathbb{O}_{p\times r}, let Π(U)=UUT\Pi(U)=UU^{\mathsf{T}} denote the orthogonal projector onto its column space. For any order-qq tensor M∈Rp1×⋯×pq\mathbf{M}\in\mathbb{R}^{p_1\times\cdots\times p_q} and s∈[q]s\in[q], let Ms(M)∈Rps×∏s′≠sps′\mathcal{M}_s(\mathbf{M})\in\mathbb{R}^{p_s\times\prod_{s'\neq s}p_{s'}} denote its mode-ss matricization. For B∈Rps×ps′B\in\mathbb{R}^{p_s\times p_s'}, the mode-ss product of M\mathbf{M} and BB is denoted by M×sB\mathbf{M}\times_s B. We write ⨂j=1qAj\bigotimes_{j=1}^q A_j for the Kronecker product of the matrices A1,…,AqA_1,\ldots,A_q. For probability measures P,Q\mathbb{P},\mathbb{Q}, TV⁡(P,Q)\operatorname{TV}(\mathbb{P},\mathbb{Q}) denotes the total variation distance.

The rest of this paper is organized as follows. § 2 introduces the federated model, formalizes the DP constraints, and presents the estimation procedure together with its privacy guarantee. In § 3, we state the model assumptions and derive the non-asymptotic upper bound as well as establishing the matching minimax lower bound. § 4 develops the private calibration procedure and establishes that the adaptive estimator preserves the privacy guarantee and attains the oracle rate. Monte Carlo experiments and a real data application are presented in § 5, followed by a discussion of possible extensions in § 6. Proofs and auxiliary results are deferred to the supplementary material.

Methodology

In this section, we develop a federated estimator of a common mode-wise loading space from tensor-valued observations and establish its FDP guarantee. We first formulate the federated Tucker tensor factor model and define the relevant notions of DP in § 2.1. The proposed estimator is presented in § 2.2, and its privacy guarantee is established through sensitivity analysis in § 2.3.

Federated model and differential privacy

We consider a federated setting with mm local clients. Client j∈[m]j \in[m] observes njn_j order-KK tensors, collected in the dataset Dj=(X1(j),…,Xnj(j))∈ZnjD_j = (X_1^{(j)}, \ldots, X_{n_j}^{(j)}) \in\mathcal{Z}^{n_j}, where Z=Rp1×⋯×pK\mathcal{Z} = \mathbb{R}^{p_1 \times\cdots\times p_K}. For each j∈[m]j \in[m] and t∈[nj]t \in[n_j], we assume that the data follow a Tucker tensor factor model

Xt(j)=St(j)+Et(j),where St(j)=Ft(j)×1A1×2⋯×KAK.(1)X_t^{(j)} = S_t^{(j)} + E_t^{(j)}, \qquad\text{where } S_t^{(j)} = F_t^{(j)} \times_1 A_1 \times_2 \cdots\times_K A_K. \tag*{(1)}

Here, Ft(j)∈Rr1×⋯×rKF_t^{(j)} \in\mathbb{R}^{r_1 \times\cdots\times r_K} is the client-specific core factor tensor, Ak∈Rpk×rkA_k \in\mathbb{R}^{p_k \times r_k} is the mode-kk loading matrix, and Et(j)E_t^{(j)} is the idiosyncratic noise. We assume that all clients share the same mode-wise loading spaces, while their latent factors and factor strengths may differ. Such an assumption is a natural one when clients collect comparable tensor-valued observations with aligned modes, as in the multi-hospital, multi-center, and multi-platform applications discussed in § 1. The common loading spaces capture shared mode-wise structures, whereas the client-specific latent factors accommodate heterogeneity across clients.

Even when the loading matrices differ across the clients as St(j)=Ft(j)×1A1(j)×2⋯×KAK(j)S_t^{(j)} = F_t^{(j)} \times_1 A_1^{(j)} \times_2 \cdots\times_K A_K^{(j)}, if there exist AkA_k and Bk(j)∈Rrk×rkB_k^{(j)} \in\mathbb{R}^{r_k \times r_k} satisfying Ak(j)=AkBk(j)A_k^{(j)} = A_k B_k^{(j)} for all j∈[m]j \in[m], the cross-client heterogeneity can be absorbed into the client-specific core factor, by noting that

St(j)=(Ft(j)×1B1(j)×2⋯×KBK(j))×1A1×2⋯×KAK.S_t^{(j)} = \left(F_t^{(j)} \times_1 B_1^{(j)} \times_2 \cdots\times_K B_K^{(j)}\right) \times_1 A_1 \times_2 \cdots\times_K A_K.

References

  1. [1]Allen, G. (2012). Sparse higher-order principal components analysis. In International Conference on Artificial Intelligence and Statistics, pages 27–36.
  2. [2]Auddy, A., Cai, T. T., and Chakraborty, A. (2026). Minimax and adaptive transfer learning for nonparametric classification under distributed differential privacy constraints. Journal of the Royal Statistical Society Series B: Statistical Methodology, 88(3):903–929.DOI
  3. [3]Babii, A., Ghysels, E., and Pan, J. (2025). Tensor PCA for factor models. Journal of Econometrics, page 106077.
  4. [4]Bai, J. and Li, K. (2012). Statistical analysis of factor models of high dimension. The Annals of Statistics, 40(1):436 – 465.DOI
  5. [5]Barigozzi, M., Cho, H., and Maeng, H. (2026a). Tail-robust factor modelling of vector and tensor time series in high dimensions. Biometrika, 113(2):asaf093.arxiv.org/abs/2407.09390
  6. [6]Barigozzi, M., He, Y., Li, L., and Trapani, L. (2026b). Statistical inference for large-dimensional tensor factor model by iterative projections. Journal of Multivariate Analysis, 214:105616.arxiv.org/abs/2206.09800
  7. [7]Blum, A., Dwork, C., McSherry, F., and Nissim, K. (2005). Practical privacy: the sulq framework. In Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, pages 128–138.
  8. [8]Bolivar, S., Huang, S.-C., and Chen, R. (2026). Analysis of tensor time series. Annual Review of Statistics and Its Application, 13:369–398.DOI
  9. [9]Braboszcz, C., Cahn, B. R., Levy, J., Fernandez, M., and Delorme, A. (2017). Increased gamma brainwave amplitude compared to control in three different meditation traditions. PloS one, 12(1):e0170647.DOI
  10. [10]Cai, T., Chakraborty, A., and Vuursteen, L. (2024a). Optimal federated learning for functional mean estimation under heterogeneous privacy constraints. arXiv preprint arXiv:2412.18992.arxiv.org/abs/2412.18992
  11. [11]Cai, T. T., Chakraborty, A., and Vuursteen, L. (2024b). Optimal federated learning for nonparametric regression with heterogeneous distributed differential privacy constraints. arXiv preprint arXiv:2406.06755.arxiv.org/abs/2406.06755
  12. [12]Cai, T. T. and Li, Y. (2026a). A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning. arXiv preprint arXiv:2605.19813.arxiv.org/abs/2605.19813
  13. [13]Cai, T. T. and Li, Y. (2026b). Minimax and adaptive covariance matrix estimation under differential privacy. arXiv preprint arXiv:2603.19703.arxiv.org/abs/2603.19703
  14. [14]Cai, T. T., Xia, D., and Zha, M. (2024c). Optimal differentially private PCA and estimation for spiked covariance matrices. arXiv preprint arXiv:2401.03820.arxiv.org/abs/2401.03820
  15. [15]Carbery, A. and Wright, J. (2001). Distributional and Lq norm inequalities for polynomials over convex bodies in Rn. Mathematical Research Letters, 8(3):233–248.
  16. [16]Cen, Z. and Lam, C. (2025). Tensor time series imputation through tensor factor modelling. Journal of Econometrics, 249:105974.
  17. [17]Chaudhuri, K., Sarwate, A. D., and Sinha, K. (2013). A near-optimal algorithm for differentially-private principal components. Journal of Machine Learning Research, 14:2905–2943.DOI
  18. [18]Chen, R., Yang, D., and Zhang, C.-H. (2022). Factor models for high-dimensional tensor time series. Journal of the American Statistical Association, 117(537):94–116.
  19. [19]Chen, W. and Lam, C. (2024). Factor strength estimation in vector and matrix time series factor models. arXiv preprint arXiv:2405.07294.arxiv.org/abs/2405.07294
  20. [20]Cichocki, A., Zdunek, R., Phan, A. H., and Amari, S.-i. (2009). Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. John Wiley & Sons.DOI
  21. [21]Düngler, J. and Sanyal, A. (2026). An iterative algorithm for differentially private k-PCA with adaptive noise. Advances in Neural Information Processing Systems, 38:132205–132250.
  22. [22]Dwork, C. and Lei, J. (2009). Differential privacy and robust statistics. In Proceedings of the forty-first annual ACM symposium on Theory of computing, pages 371–380.DOI
  23. [23]Dwork, C., McSherry, F., Nissim, K., and Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In Halevi, S. and Rabin, T., editors, Theory of Cryptography, pages 265–284, Berlin, Heidelberg. Springer Berlin Heidelberg.
  24. [24]Dwork, C. and Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends® in Theoretical Computer Science, 9(3-4):211–487.
  25. [25]Dwork, C., Talwar, K., Thakurta, A., and Zhang, L. (2014). Analyze gauss: optimal bounds for privacy-preserving principal component analysis. In Proceedings of the forty-sixth annual ACM symposium on Theory of computing, pages 11–20.
  26. [26]Gill, R. D. and Levit, B. Y. (1995). Applications of the Van Trees Inequality: A Bayesian Cramér–Rao Bound. Bernoulli, 1(1–2):59–79.DOI
  27. [27]Grammenos, A., Mendoza Smith, R., Crowcroft, J., and Mascolo, C. (2020). Federated principal component analysis. Advances in Neural Information Processing Systems, 33:6453–6464.arxiv.org/abs/1907.08059
  28. [28]Gross, D. and Nesme, V. (2010). Note on sampling without replacing from a finite collection of matrices. arXiv preprint arXiv:1001.2738.
  29. [30]Han, Y., Chen, R., Yang, D., and Zhang, C.-H. (2024). Tensor factor model estimation by iterative projection. The Annals of Statistics, 52(6):2641 – 2667.
  30. [31]Han, Y., Chen, R., and Zhang, C.-H. (2022). Rank determination in tensor factor model. Electronic Journal of Statistics, 16(1):1726–1803.
  31. [32]Han, Y. and Zhang, C.-H. (2022). Tensor principal component analysis in high dimensional cp models. IEEE Transactions on Information Theory, 69(2):1147–1167.
  32. [34]Hung, E. K. and Yu, Y. (2025). Optimal cox regression under federated differential privacy: coefficients and cumulative hazards. arXiv preprint arXiv:2508.19640.
  33. [35]Jolliffe, I. T. (2002). Principal Component Analysis. Springer.
  34. [36]Jolliffe, I. T. and Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical Transactions Series A, Mathematical, Physical, and Engineering Sciences, 374(2065):20150202.
  35. [37]Karatzoglou, A., Amatriain, X., Baltrunas, L., and Oliver, N. (2010). Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems, pages 79–86. ACM.
  36. [38]Kolda, T. G. and Bader, B. W. (2009). Tensor decompositions and applications. SIAM review, 51(3):455–500.DOI
  37. [41]Liu, X., Kong, W., Jain, P., and Oh, S. (2022). DP-PCA: Statistically optimal and differentially private PCA. In Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., and Oh, A., editors, Advances in Neural Information Processing Systems, volume 35, pages 29929–29943. Curran Associates, Inc.arxiv.org/abs/2205.13709
  38. [42]McMahan, B., Moore, E., Ramage, D., Hampson, S., and Aguera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics, pages 1273–1282. PMLR.arxiv.org/abs/1602.05629
  39. [43]Onatski, A. (2012). Asymptotics of the principal components estimator of large factor models with weakly influential factors. Journal of Econometrics, 168(2):244–258.DOI
  40. [44]Pinelis, I. (1994). Optimum bounds for the distributions of martingales in banach spaces. The Annals of Probability, pages 1679–1706.arxiv.org/abs/1208.2200
  41. [45]Tropp, J. A. (2015). An introduction to matrix concentration inequalities. Foundations and Trends in Machine Learning, 8(1-2):1–230.arxiv.org/abs/1501.01571
  42. [46]Tsfadia, E. (2024). On differentially private subspace estimation in a distribution-free setting. Advances in Neural Information Processing Systems, 37:39923–39962.arxiv.org/abs/2402.06465
  43. [47]Tsfadia, E., Cohen, E., Kaplan, H., Mansour, Y., and Stemmer, U. (2022). Friendlycore: Practical differentially private aggregation. In International Conference on Machine Learning, pages 21828–21863. PMLR.arxiv.org/abs/2110.10132
  44. [48]Vershynin, R. (2018). High-dimensional Probability: An Introduction with Applications in Data Science, volume 47. Cambridge University Press.
  45. [49]Wainwright, M. J. (2019). High-dimensional statistics: A non-asymptotic viewpoint, volume 48. Cambridge University Press.
  46. [50]Wang, D., Liu, X., and Chen, R. (2019). Factor models for matrix-valued high-dimensional time series. Journal of Econometrics, 208(1):231–248. Special Issue on Financial Engineering and Risk Management.arxiv.org/abs/1610.01889
  47. [51]Wang, D. and Xu, J. (2020). Principal component analysis in the local differential privacy model. Theoretical Computer Science, 809:296–312.
  48. [52]Wei, K., Li, J., Ding, M., Ma, C., Yang, H. H., Farokhi, F., Jin, S., Quek, T. Q., and Poor, H. V. (2020). Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security, 15:3454–3469.arxiv.org/abs/1911.00222
  49. [53]Xue, G., Lin, Z., and Yu, Y. (2024). Optimal estimation in private distributed functional data analysis. arXiv preprint arXiv:2412.06582.arxiv.org/abs/2412.06582
  50. [54]Yang, Y. and Ma, C. (2025). Estimating shared subspace with ajive: the power and limitation of multiple data matrices. arXiv preprint arXiv:2501.09336.arxiv.org/abs/2501.09336
  51. [56]Zhang, Y., Cen, Z., and Cho, H. (2026). Detection and mode-identification of multiple change points in tensor factor models. arXiv preprint arXiv:2604.11300v1.arxiv.org/abs/2604.11300
  52. [57]Zhao, P., Lai, L., Shen, L., Li, Q., Wu, J., and Liu, Z. (2024). A huber loss minimization approach to mean estimation under user-level differential privacy. Advances in Neural Information Processing Systems, 37:130018–130056.arxiv.org/abs/2405.13453

Paper details

vlnc:W_erdy65t3
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 8

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents