List-Decodable Covariance Estimation

• URL: http://arxiv.org/abs/2206.10942v1
• Date: Wed, 22 Jun 2022 09:38:06 GMT
• Title: List-Decodable Covariance Estimation
• Authors: Misha Ivkov and Pravesh K. Kothari
• Abstract summary: We give the first time algorithm for emphlist-decodable covariance estimation. Our result implies the first-time emphexact algorithm for list-decodable linear regression and subspace recovery.
• Score: 1.9290392443571387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We give the first polynomial time algorithm for \emph{list-decodable covariance estimation}. For any $\alpha > 0$, our algorithm takes input a sample $Y \subseteq \mathbb{R}^d$ of size $n\geq d^{\mathsf{poly}(1/\alpha)}$ obtained by adversarially corrupting an $(1-\alpha)n$ points in an i.i.d. sample $X$ of size $n$ from the Gaussian distribution with unknown mean $\mu_*$ and covariance $\Sigma_*$. In $n^{\mathsf{poly}(1/\alpha)}$ time, it outputs a constant-size list of $k = k(\alpha)= (1/\alpha)^{\mathsf{poly}(1/\alpha)}$ candidate parameters that, with high probability, contains a $(\hat{\mu},\hat{\Sigma})$ such that the total variation distance $TV(\mathcal{N}(\mu_*,\Sigma_*),\mathcal{N}(\hat{\mu},\hat{\Sigma}))<1-O_{\alpha}(1)$. This is the statistically strongest notion of distance and implies multiplicative spectral and relative Frobenius distance approximation for parameters with dimension independent error. Our algorithm works more generally for $(1-\alpha)$-corruptions of any distribution $D$ that possesses low-degree sum-of-squares certificates of two natural analytic properties: 1) anti-concentration of one-dimensional marginals and 2) hypercontractivity of degree 2 polynomials. Prior to our work, the only known results for estimating covariance in the list-decodable setting were for the special cases of list-decodable linear regression and subspace recovery due to Karmarkar, Klivans, and Kothari (2019), Raghavendra and Yau (2019 and 2020) and Bakshi and Kothari (2020). These results need superpolynomial time for obtaining any subconstant error in the underlying dimension. Our result implies the first polynomial-time \emph{exact} algorithm for list-decodable linear regression and subspace recovery that allows, in particular, to obtain $2^{-\mathsf{poly}(d)}$ error in polynomial-time. Our result also implies an improved algorithm for clustering non-spherical mixtures.

Related papers

• Dimension-free Private Mean Estimation for Anisotropic Distributions [55.86374912608193]
  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.
  arXiv  Detail & Related papers  (2024-11-01T17:59:53Z)
• Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians [7.04316974339151]
  We study the estimation of distributional parameters when samples are shown only if they fall in some unknown set. We develop tools that may be of independent interest, including a reduction from PAC learning with positive and unlabeled samples to PAC learning with positive and negative samples.
  arXiv  Detail & Related papers  (2024-10-02T15:21:07Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering [42.526664955704746]
  We develop a novel, conceptually simpler technique for list-decodable sparse mean estimation. In particular, for distributions with "certifiably bounded" $t-th moments in $k$-sparse directions, our algorithm achieves error of $(1/alpha)O (1/t)$ with sample complexity $m = (klog(n))O(t)/alpha(mnt)$. For the special case of Gaussian inliers, our algorithm achieves the optimal error guarantee of $Theta (sqrtlog
  arXiv  Detail & Related papers  (2022-06-10T17:38:18Z)
• Clustering Mixture Models in Almost-Linear Time via List-Decodable Mean Estimation [58.24280149662003]
  We study the problem of list-decodable mean estimation, where an adversary can corrupt a majority of the dataset. We develop new algorithms for list-decodable mean estimation, achieving nearly-optimal statistical guarantees.
  arXiv  Detail & Related papers  (2021-06-16T03:34:14Z)
• Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models [56.98280399449707]
  We show that there exists an $epsilon$-cover for $S$ of cardinality $M = (k/epsilon)O_d(k1/d)$. Building on our structural result, we obtain significantly improved learning algorithms for several fundamental high-dimensional probabilistic models hidden variables.
  arXiv  Detail & Related papers  (2020-12-14T18:14:08Z)
• List-Decodable Mean Estimation in Nearly-PCA Time [50.79691056481693]
  We study the fundamental task of list-decodable mean estimation in high dimensions. Our algorithm runs in time $widetildeO(ndk)$ for all $k = O(sqrtd) cup Omega(d)$, where $n$ is the size of the dataset. A variant of our algorithm has runtime $widetildeO(ndk)$ for all $k$, at the expense of an $O(sqrtlog k)$ factor in the recovery guarantee
  arXiv  Detail & Related papers  (2020-11-19T17:21:37Z)
• Optimal Robust Linear Regression in Nearly Linear Time [97.11565882347772]
  We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = langle X,w* rangle + epsilon$ We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $mathbbE [XXtop]$ has bounded condition number and $epsilon$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $epsilon$ is
  arXiv  Detail & Related papers  (2020-07-16T06:44:44Z)
• Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time [14.990725929840892]
  We show an algorithm that runs in time $widetildeO(T(N, d) log kappa / mathrmpoly (varepsilon))$, where $T(N, d)$ is the time it takes to multiply a $d times N$ matrix by its transpose. Our runtime matches that of the fastest algorithm for covariance estimation without outliers, up to poly-logarithmic factors.
  arXiv  Detail & Related papers  (2020-06-23T20:21:27Z)
• List-Decodable Subspace Recovery: Dimension Independent Error in Polynomial Time [5.812499828391904]
  In list-decodable subspace recovery, the input is a collection of $n$ points $alpha n$ (for some $alpha ll 1/2$) of which are drawn i.i.d. from a distribution $mathcalD$. In this work, we improve on results on all three fronts: emphcertifiable anti-concentration error via a faster fixed-polynomial running time.
  arXiv  Detail & Related papers  (2020-02-12T18:30:09Z)

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.