ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1710.00956
16
5

Monte Carlo approximation certificates for k-means clustering

3 October 2017
D. Mixon
Soledad Villar
ArXivPDFHTML
Abstract

Efficient algorithms for kkk-means clustering frequently converge to suboptimal partitions, and given a partition, it is difficult to detect kkk-means optimality. In this paper, we develop an a posteriori certifier of approximate optimality for kkk-means clustering. The certifier is a sub-linear Monte Carlo algorithm based on Peng and Wei's semidefinite relaxation of kkk-means. In particular, solving the relaxation for small random samples of the dataset produces a high-confidence lower bound on the kkk-means objective, and being sub-linear, our algorithm is faster than kkk-means++ when the number of data points is large. We illustrate the performance of our algorithm with both numerical experiments and a performance guarantee: If the data points are drawn independently from any mixture of two Gaussians over Rm\mathbb{R}^mRm with identity covariance, then with probability 1−O(1/m)1-O(1/m)1−O(1/m), our poly⁡(m)\operatorname{poly}(m)poly(m)-time algorithm produces a 3-approximation certificate with 99% confidence.

View on arXiv
Comments on this paper