Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures

• URL: http://arxiv.org/abs/2411.12438v1
• Date: Tue, 19 Nov 2024 11:58:51 GMT
• Title: Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures
• Authors: Prashanti Anderson, Mitali Bafna, Rares-Darius Buhai, Pravesh K. Kothari, David Steurer,
• Abstract summary: We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition. Our algorithms naturally extend to tolerating a dimension-independent fraction of arbitrary outliers.
• Score: 5.668124846154999
• License:
• Abstract: We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input data. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition, that forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang [VW04] (in addition to several other applications). As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation separated mixture of $k$ centered (i.e., zero-mean) Gaussians with $n\geq \operatorname{poly}(d) f(w_{\min}^{-1})$ samples and $\operatorname{poly}(n)$ time, and (2) cluster an arbitrary total-variation separated mixture of $k$ Gaussians with identical but arbitrary unknown covariance with $n \geq d^{O(\log w_{\min}^{-1})} f(w_{\min}^{-1})$ samples and $n^{O(\log w_{\min}^{-1})}$ time. Here, $w_{\min}$ is the minimum mixing weight of the input mixture, and $f$ does not depend on the dimension $d$. Our algorithms naturally extend to tolerating a dimension-independent fraction of arbitrary outliers. Before this work, the techniques in the state-of-the-art non-spherical clustering algorithms needed $d^{O(k)} f(w_{\min}^{-1})$ time and samples for clustering such mixtures. Our results may come as a surprise in the context of the $d^{\Omega(k)}$ statistical query lower bound [DKS17] for clustering non-spherical Gaussian mixtures. While this result is usually thought to rule out $d^{o(k)}$ cost algorithms for the problem, our results show that the lower bounds can in fact be circumvented for a remarkably general class of Gaussian mixtures.

Related papers

• Learning general Gaussian mixtures with efficient score matching [16.06356123715737]
  We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components. We give an algorithm that draws $dmathrmpoly(k/varepsilon)$ samples from the target mixture, runs in sample-polynomial time, and constructs a sampler.
  arXiv  Detail & Related papers  (2024-04-29T17:30:36Z)
• Clustering Mixtures of Bounded Covariance Distributions Under Optimal Separation [44.25945344950543]
  We study the clustering problem for mixtures of bounded covariance distributions. We give the first poly-time algorithm for this clustering task. Our algorithm is robust to $Omega(alpha)$-fraction of adversarial outliers.
  arXiv  Detail & Related papers  (2023-12-19T01:01:53Z)
• Do you know what q-means? [50.045011844765185]
  Clustering is one of the most important tools for analysis of large datasets. We present an improved version of the "$q$-means" algorithm for clustering. We also present a "dequantized" algorithm for $varepsilon which runs in $Obig(frack2varepsilon2(sqrtkd + log(Nd))big.
  arXiv  Detail & Related papers  (2023-08-18T17:52:12Z)
• Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise [50.64137465792738]
  We show that any efficient SQ algorithm for the problem requires sample complexity at least $Omega(d1/2/(maxp, epsilon)2)$. Our lower bound suggests that this quadratic dependence on $1/epsilon$ is inherent for efficient algorithms.
  arXiv  Detail & Related papers  (2023-07-13T18:59:28Z)
• A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm [41.03423042792559]
  We produce a list of hypotheses that are close to $Sigma$ in relative Frobenius norm. As a corollary, we obtain an efficient spectral algorithm for robust partial clustering of Gaussian mixture models. Our new method yields the first Sum-of-Squares-free algorithm for robustly learning GMMs.
  arXiv  Detail & Related papers  (2023-05-01T17:54:35Z)
• Replicable Clustering [57.19013971737493]
  We propose algorithms for the statistical $k$-medians, statistical $k$-means, and statistical $k$-centers problems by utilizing approximation routines for their counterparts in a black-box manner. We also provide experiments on synthetic distributions in 2D using the $k$-means++ implementation from sklearn as a black-box that validate our theoretical results.
  arXiv  Detail & Related papers  (2023-02-20T23:29:43Z)
• Private estimation algorithms for stochastic block models and mixture models [63.07482515700984]
  General tools for designing efficient private estimation algorithms. First efficient $(epsilon, delta)$-differentially private algorithm for both weak recovery and exact recovery.
  arXiv  Detail & Related papers  (2023-01-11T09:12:28Z)
• 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)
• No-substitution k-means Clustering with Adversarial Order [8.706058694927613]
  We introduce a new complexity measure that quantifies the difficulty of clustering a dataset arriving in arbitrary order. Our new algorithm takes only $textpoly(klog(n))$ centers and is a $textpoly(k)$-approximation.
  arXiv  Detail & Related papers  (2020-12-28T22:35:44Z)
• Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
  We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting. We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$. Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
  arXiv  Detail & Related papers  (2020-05-13T16:44:12Z)
• Outlier-Robust Clustering of Non-Spherical Mixtures [5.863264019032882]
  We give the first outlier-robust efficient algorithm for clustering a mixture of $k$ statistically separated d-dimensional Gaussians (k-GMMs) Our results extend to clustering mixtures of arbitrary affine transforms of the uniform distribution on the $d$-dimensional unit sphere.
  arXiv  Detail & Related papers  (2020-05-06T17:24:27Z)

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.