Towards Optimal Lower Bounds for k-median and k-means Coresets

• URL: http://arxiv.org/abs/2202.12793v1
• Date: Fri, 25 Feb 2022 16:13:28 GMT
• Title: Towards Optimal Lower Bounds for k-median and k-means Coresets
• Authors: Vincent Cohen-Addad, Kasper Green Larsen, David Saulpic, Chris Schwiegelshohn
• Abstract summary: Given a set of points in a metric space, the $(k,z)$-clustering problem consists of finding a set of $k$ points called centers. We show that any coreset for $(k,z)$ clustering must consist of at least $Omega(k varepsilon-2 log n)$ and $Omega(k varepsilon-2 D)$ points.
• Score: 25.713987341159918
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given a set of points in a metric space, the $(k,z)$-clustering problem consists of finding a set of $k$ points called centers, such that the sum of distances raised to the power of $z$ of every data point to its closest center is minimized. Special cases include the famous k-median problem ($z = 1$) and k-means problem ($z = 2$). The $k$-median and $k$-means problems are at the heart of modern data analysis and massive data applications have given raise to the notion of coreset: a small (weighted) subset of the input point set preserving the cost of any solution to the problem up to a multiplicative $(1 \pm \varepsilon)$ factor, hence reducing from large to small scale the input to the problem. In this paper, we present improved lower bounds for coresets in various metric spaces. In finite metrics consisting of $n$ points and doubling metrics with doubling constant $D$, we show that any coreset for $(k,z)$ clustering must consist of at least $\Omega(k \varepsilon^{-2} \log n)$ and $\Omega(k \varepsilon^{-2} D)$ points, respectively. Both bounds match previous upper bounds up to polylog factors. In Euclidean spaces, we show that any coreset for $(k,z)$ clustering must consists of at least $\Omega(k\varepsilon^{-2})$ points. We complement these lower bounds with a coreset construction consisting of at most $\tilde{O}(k\varepsilon^{-2}\cdot \min(\varepsilon^{-z},k))$ points.

Related papers

• The Communication Complexity of Approximating Matrix Rank [50.6867896228563]
  We show that this problem has randomized communication complexity $Omega(frac1kcdot n2log|mathbbF|)$. As an application, we obtain an $Omega(frac1kcdot n2log|mathbbF|)$ space lower bound for any streaming algorithm with $k$ passes.
  arXiv  Detail & Related papers  (2024-10-26T06:21:42Z)
• Nearly Linear Sparsification of $\ell_p$ Subspace Approximation [47.790126028106734]
  A popular approach to cope with the NP-hardness of the $ell_p$ subspace approximation problem is to compute a strong coreset. We obtain the first algorithm for constructing a strong coreset for $ell_p$ subspace approximation with a nearly optimal dependence on the rank parameter $k$. Our techniques also lead to the first nearly optimal online strong coresets for $ell_p$ subspace approximation with similar bounds as the offline setting.
  arXiv  Detail & Related papers  (2024-07-03T16:49:28Z)
• Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming [48.18845814885398]
  We develop new techniques to extend the applicability of sketching-based approaches to sparse dictionary learning and the Euclidean $k$-means clustering problems. On the fast algorithms front, we obtain a new approach for designing PTAS's for the $k$-means clustering problem. On the streaming algorithms front, we obtain new upper bounds and lower bounds for dictionary learning and $k$-means clustering.
  arXiv  Detail & Related papers  (2023-10-29T16:46:26Z)
• The Computational Complexity of Finding Stationary Points in Non-Convex Optimization [53.86485757442486]
  Finding approximate stationary points, i.e., points where the gradient is approximately zero, of non-order but smooth objective functions is a computational problem. We show that finding approximate KKT points in constrained optimization is reducible to finding approximate stationary points in unconstrained optimization but the converse is impossible.
  arXiv  Detail & Related papers  (2023-10-13T14:52:46Z)
• On Generalization Bounds for Projective Clustering [3.4490841399255823]
  Given a set of points, clustering consists of finding a partition of a point set into $k$ clusters such that the center to which a point is assigned is as close as possible. For center-based objectives, we show a convergence rate of $tildeOleft(sqrtfrackj2nright)$. For subspace clustering with $j$-dimensional subspaces, we show a convergence rate of $tildeOleft(sqrtfrackj2nright)$.
  arXiv  Detail & Related papers  (2023-10-13T14:15:54Z)
• 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)
• Parameterized Approximation for Robust Clustering in Discrete Geometric Spaces [2.687607197645453]
  We show that even the special case of $k$-Center in dimension $Theta(log n)$ is $(sqrt3/2- o(1))$hard to approximate for FPT algorithms. We also show that even the special case of $k$-Center in dimension $Theta(log n)$ is $(sqrt3/2- o(1))$hard to approximate for FPT algorithms.
  arXiv  Detail & Related papers  (2023-05-12T08:43:28Z)
• Improved Coresets for Euclidean $k$-Means [24.850829728643923]
  Given a set of $n$ points in $d$ dimensions, the Euclidean $k$-means problem (resp. the Euclidean $k$-median problem) consists of finding $k$ centers. In this paper, we improve the upper bounds $tilde O(min(k2 cdot varepsilon-2,kcdot varepsilon-4)$ for $k$-means and $tilde O(min(k4/3 cdot varepsilon
  arXiv  Detail & Related papers  (2022-11-15T14:47:24Z)
• Streaming Complexity of SVMs [110.63976030971106]
  We study the space complexity of solving the bias-regularized SVM problem in the streaming model. We show that for both problems, for dimensions of $frac1lambdaepsilon$, one can obtain streaming algorithms with spacely smaller than $frac1lambdaepsilon$.
  arXiv  Detail & Related papers  (2020-07-07T17:10:00Z)
• Sets Clustering [25.358415142404752]
  We prove that a core-set of $O(logn)$ sets always exists, and can be computed in $O(nlogn)$ time. Applying an inefficient but optimal algorithm on this coreset allows us to obtain the first PTAS ($1+varepsilon$ approximation) for the sets-$k$-means problem. Open source code and experimental results for document classification and facility locations are also provided.
  arXiv  Detail & Related papers  (2020-03-09T13:30:30Z)

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.