Differentially Private Fr\'echet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices

• URL: http://arxiv.org/abs/2208.04245v1
• Date: Mon, 8 Aug 2022 16:15:14 GMT
• Title: Differentially Private Fr\'echet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices
• Abstract summary: We propose a novel, simple and fast mechanism to compute a differentially private Frechet mean on the SPD manifold. We show that our new mechanism obtains quadratic utility improvement in terms of data dimension over the current and only available baseline.
• Score: 4.917075909999548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential privacy has become crucial in the real-world deployment of statistical and machine learning algorithms with rigorous privacy guarantees. The earliest statistical queries, for which differential privacy mechanisms have been developed, were for the release of the sample mean. In Geometric Statistics, the sample Fr\'echet mean represents one of the most fundamental statistical summaries, as it generalizes the sample mean for data belonging to nonlinear manifolds. In that spirit, the only geometric statistical query for which a differential privacy mechanism has been developed, so far, is for the release of the sample Fr\'echet mean: the \emph{Riemannian Laplace mechanism} was recently proposed to privatize the Fr\'echet mean on complete Riemannian manifolds. In many fields, the manifold of Symmetric Positive Definite (SPD) matrices is used to model data spaces, including in medical imaging where privacy requirements are key. We propose a novel, simple and fast mechanism - the \emph{Tangent Gaussian mechanism} - to compute a differentially private Fr\'echet mean on the SPD manifold endowed with the log-Euclidean Riemannian metric. We show that our new mechanism obtains quadratic utility improvement in terms of data dimension over the current and only available baseline. Our mechanism is also simpler in practice as it does not require any expensive Markov Chain Monte Carlo (MCMC) sampling, and is computationally faster by multiple orders of magnitude -- as confirmed by extensive experiments.

Related papers

• Geometric Renyi Differential Privacy: Ricci Curvature Characterized by Heat Diffusion Mechanisms [4.997037172860666]
  Key contribution lies in uncovering unexpected connections among geometric analysis, heat diffusion models, and differential privacy.<n>We establish Renyi differential privacy guarantees governed by Ricci curvature.<n>For manifold with nonnegative Ricci curvature, we propose a mechanism based on heat diffusion.<n>As a statistical application, we develop privacy-preserving estimation of the generalized Frechet mean.
  arXiv  Detail & Related papers  (2026-04-22T16:48:55Z)
• Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation [6.087515951830486]
  We study privacy amplification for differentially private model training with matrix factorization under random allocation.<n>Our framework applies to arbitrary banded and non-banded matrices.
  arXiv  Detail & Related papers  (2026-01-29T12:40:29Z)
• CLT and Edgeworth Expansion for m-out-of-n Bootstrap Estimators of The Studentized Median [4.174296652683762]
  The m-out-of-n bootstrap approximates the distribution of a statistic by repeatedly drawing m subsamples without replacement from an original sample of size n.<n>Despite its broad applicability across econometrics, biostatistics, and machine learning, rigorous parameter-free guarantees for the soundness of the bootstrap have remained elusive.<n>This paper establishes such guarantees by analyzing the estimator of sample quantiles obtained from m-out-of-n resampling of a dataset of size n.
  arXiv  Detail & Related papers  (2025-05-16T22:14:49Z)
• Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices [6.7523635840772505]
  Circular and non-flat data distributions are prevalent across diverse domains of data science. A principled approach to accounting for the underlying geometry of such data is pivotal. This work lays the groundwork for extending classical machine learning and statistical methods to more complex and structured data.
  arXiv  Detail & Related papers  (2025-02-03T16:46:46Z)
• Differentially Private Random Feature Model [52.468511541184895]
  We produce a differentially private random feature model for privacy-preserving kernel machines. We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Exactly Minimax-Optimal Locally Differentially Private Sampling [12.587817635325266]
  We define the fundamental PUT of private sampling in the minimax sense, using the f-divergence between original and sampling distributions as the utility measure. We characterize the exact PUT for both finite and continuous data spaces under mild conditions on the data distributions, and propose sampling mechanisms that are universally optimal for all f-divergences.
  arXiv  Detail & Related papers  (2024-10-30T05:13:18Z)
• Conformal inference for regression on Riemannian Manifolds [49.7719149179179]
  We investigate prediction sets for regression scenarios when the response variable, denoted by $Y$, resides in a manifold, and the covariable, denoted by X, lies in Euclidean space. We prove the almost sure convergence of the empirical version of these regions on the manifold to their population counterparts.
  arXiv  Detail & Related papers  (2023-10-12T10:56:25Z)
• Simplex Random Features [53.97976744884616]
  We present Simplex Random Features (SimRFs), a new random feature (RF) mechanism for unbiased approximation of the softmax and Gaussian kernels. We prove that SimRFs provide the smallest possible mean square error (MSE) on unbiased estimates of these kernels. We show consistent gains provided by SimRFs in settings including pointwise kernel estimation, nonparametric classification and scalable Transformers.
  arXiv  Detail & Related papers  (2023-01-31T18:53:39Z)
• Test Set Sizing Via Random Matrix Theory [91.3755431537592]
  This paper uses techniques from Random Matrix Theory to find the ideal training-testing data split for a simple linear regression. It defines "ideal" as satisfying the integrity metric, i.e. the empirical model error is the actual measurement noise. This paper is the first to solve for the training and test size for any model in a way that is truly optimal.
  arXiv  Detail & Related papers  (2021-12-11T13:18:33Z)
• Differential Privacy Over Riemannian Manifolds [9.453554184019108]
  We present an extension of the Laplace or K-norm mechanism that utilizes intrinsic distances and volumes on the manifold. We demonstrate that our mechanism is rate optimal and depends only on the dimension of the manifold, not on the dimension of any ambient space.
  arXiv  Detail & Related papers  (2021-11-03T20:43:54Z)
• Dimension Reduction and Data Visualization for Fr\'echet Regression [8.713190936209156]
  Fr'echet regression model provides a promising framework for regression analysis with metric spacevalued responses. We introduce a flexible sufficient dimension reduction (SDR) method for Fr'echet regression to achieve two purposes.
  arXiv  Detail & Related papers  (2021-10-01T15:01:32Z)
• Bayesian Quadrature on Riemannian Data Manifolds [79.71142807798284]
  A principled way to model nonlinear geometric structure inherent in data is provided. However, these operations are typically computationally demanding. In particular, we focus on Bayesian quadrature (BQ) to numerically compute integrals over normal laws. We show that by leveraging both prior knowledge and an active exploration scheme, BQ significantly reduces the number of required evaluations.
  arXiv  Detail & Related papers  (2021-02-12T17:38:04Z)
• Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees [25.996994681543903]
  (Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. Previous research on this problem has already lead to the discovery of some Differentially Private (DP) algorithms for (Gradient) EM. We propose in this paper the first DP version of (Gradient) EM algorithm with statistical guarantees.
  arXiv  Detail & Related papers  (2020-10-22T03:41:19Z)
• On the minmax regret for statistical manifolds: the role of curvature [68.8204255655161]
  Two-part codes and the minimum description length have been successful in delivering procedures to single out the best models. We derive a sharper expression than the standard one given by the complexity, where the scalar curvature of the Fisher information metric plays a dominant role.
  arXiv  Detail & Related papers  (2020-07-06T17:28:19Z)
• Generalized Sliced Distances for Probability Distributions [47.543990188697734]
  We introduce a broad family of probability metrics, coined as Generalized Sliced Probability Metrics (GSPMs) GSPMs are rooted in the generalized Radon transform and come with a unique geometric interpretation. We consider GSPM-based gradient flows for generative modeling applications and show that under mild assumptions, the gradient flow converges to the global optimum.
  arXiv  Detail & Related papers  (2020-02-28T04:18:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.