Dimension-free Private Mean Estimation for Anisotropic Distributions

• URL: http://arxiv.org/abs/2411.00775v1
• Date: Fri, 01 Nov 2024 17:59:53 GMT
• Title: Dimension-free Private Mean Estimation for Anisotropic Distributions
• Authors: Yuval Dagan, Michael I. Jordan, Xuelin Yang, Lydia Zakynthinou, Nikita Zhivotovskiy,
• Abstract summary: Previous private estimators on distributions over $mathRd suffer from a curse of dimensionality. We present an algorithm whose sample complexity has improved dependence on dimension.
• Score: 55.86374912608193
• License:
• Abstract: We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over $\mathbb{R}^d$ suffer from a curse of dimensionality, as they require $\Omega(d^{1/2})$ samples to achieve non-trivial error, even in cases where $O(1)$ samples suffice without privacy. This rate is unavoidable when the distribution is isotropic, namely, when the covariance is a multiple of the identity matrix, or when accuracy is measured with respect to the affine-invariant Mahalanobis distance. Yet, real-world data is often highly anisotropic, with signals concentrated on a small number of principal components. We develop estimators that are appropriate for such signals$\unicode{x2013}$our estimators are $(\varepsilon,\delta)$-differentially private and have sample complexity that is dimension-independent for anisotropic subgaussian distributions. Given $n$ samples from a distribution with known covariance-proxy $\Sigma$ and unknown mean $\mu$, we present an estimator $\hat{\mu}$ that achieves error $\|\hat{\mu}-\mu\|_2\leq \alpha$, as long as $n\gtrsim\mathrm{tr}(\Sigma)/\alpha^2+ \mathrm{tr}(\Sigma^{1/2})/(\alpha\varepsilon)$. In particular, when $\pmb{\sigma}^2=(\sigma_1^2, \ldots, \sigma_d^2)$ are the singular values of $\Sigma$, we have $\mathrm{tr}(\Sigma)=\|\pmb{\sigma}\|_2^2$ and $\mathrm{tr}(\Sigma^{1/2})=\|\pmb{\sigma}\|_1$, and hence our bound avoids dimension-dependence when the signal is concentrated in a few principal components. We show that this is the optimal sample complexity for this task up to logarithmic factors. Moreover, for the case of unknown covariance, we present an algorithm whose sample complexity has improved dependence on the dimension, from $d^{1/2}$ to $d^{1/4}$.

Related papers

• Measuring quantum relative entropy with finite-size effect [53.64687146666141]
  We study the estimation of relative entropy $D(rho|sigma)$ when $sigma$ is known. Our estimator attains the Cram'er-Rao type bound when the dimension $d$ is fixed.
  arXiv  Detail & Related papers  (2024-06-25T06:07:20Z)
• Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories [70.90012822736988]
  Existing theories on deep nonparametric regression have shown that when the input data lie on a low-dimensional manifold, deep neural networks can adapt to intrinsic data structures. This paper introduces a relaxed assumption that input data are concentrated around a subset of $mathbbRd$ denoted by $mathcalS$, and the intrinsic dimension $mathcalS$ can be characterized by a new complexity notation -- effective Minkowski dimension.
  arXiv  Detail & Related papers  (2023-06-26T17:13:31Z)
• Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions [8.40077201352607]
  We present a fast, differentially private algorithm for high-dimensional covariance-aware mean estimation. Our algorithm produces $tildemu$ such that $|mu|_Sigma leq alpha$ as long as $n gtrsim tfrac d alpha2 + tfracd sqrtlog 1/deltaalpha varepsilon+fracdlog 1/deltavarepsilon$.
  arXiv  Detail & Related papers  (2023-01-28T16:57:46Z)
• Statistically Optimal Robust Mean and Covariance Estimation for Anisotropic Gaussians [3.5788754401889014]
  In the strong $varepsilon$-contamination model we assume that the adversary replaced an $varepsilon$ fraction of vectors in the original Gaussian sample by any other vectors. We construct an estimator $widehat Sigma of the cofrac matrix $Sigma that satisfies, with probability at least $1 - delta.
  arXiv  Detail & Related papers  (2023-01-21T23:28:55Z)
• A Fast Algorithm for Adaptive Private Mean Estimation [5.090363690988394]
  We design an $(varepsilon, delta)$-differentially private algorithm that is adaptive to $Sigma$. The estimator achieves optimal rates of convergence with respect to the induced Mahalanobis norm $||cdot||_Sigma$.
  arXiv  Detail & Related papers  (2023-01-17T18:44:41Z)
• Random matrices in service of ML footprint: ternary random features with no performance loss [55.30329197651178]
  We show that the eigenspectrum of $bf K$ is independent of the distribution of the i.i.d. entries of $bf w$. We propose a novel random technique, called Ternary Random Feature (TRF) The computation of the proposed random features requires no multiplication and a factor of $b$ less bits for storage compared to classical random features.
  arXiv  Detail & Related papers  (2021-10-05T09:33:49Z)
• Nonasymptotic one-and two-sample tests in high dimension with unknown covariance structure [0.0]
  We consider the problem of testing if $mu is $eta-close to zero, i.e. $|mu| leq eta against $|mu| geq (eta + delta)$. The aim of this paper is to obtain nonasymptotic upper and lower bounds on the minimal separation distancedelta$ such that we can control both the Type I and Type II errors at a given level.
  arXiv  Detail & Related papers  (2021-09-01T06:22:53Z)
• The Sample Complexity of Robust Covariance Testing [56.98280399449707]
  We are given i.i.d. samples from a distribution of the form $Z = (1-epsilon) X + epsilon B$, where $X$ is a zero-mean and unknown covariance Gaussian $mathcalN(0, Sigma)$. In the absence of contamination, prior work gave a simple tester for this hypothesis testing task that uses $O(d)$ samples. We prove a sample complexity lower bound of $Omega(d2)$ for $epsilon$ an arbitrarily small constant and $gamma
  arXiv  Detail & Related papers  (2020-12-31T18:24:41Z)
• Estimation of Shortest Path Covariance Matrices [21.772761365915176]
  We study the sample complexity of estimating the covariance matrix $mathbfSigma in mathbbRdtimes d$ of a distribution $mathcal D$ over $mathbbRd$ given independent samples. We give a very simple algorithm for estimating $mathbfSigma$ up to norm error $epsilon left|mathbfSigmaright|$ using just $O(sqrtD)$ entry complexity and $tilde O(r
  arXiv  Detail & Related papers  (2020-11-19T17:37:46Z)
• Agnostic Learning of a Single Neuron with Gradient Descent [92.7662890047311]
  We consider the problem of learning the best-fitting single neuron as measured by the expected square loss. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$.
  arXiv  Detail & Related papers  (2020-05-29T07:20:35Z)

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.