English
Related papers

Related papers: Simple and sharp analysis of k-means||

200 papers

We give a simple deterministic $O(\log K / \log\log K)$ approximation algorithm for the Min-Max Selecting Items problem, where $K$ is the number of scenarios. While our main goal is simplicity, this result also improves over the previous…

Data Structures and Algorithms · Computer Science 2013-04-30 Benjamin Doerr

We analyze online \cite{BottouBengio} and mini-batch \cite{Sculley} $k$-means variants. Both scale up the widely used $k$-means algorithm via stochastic approximation, and have become popular for large-scale clustering and unsupervised…

Machine Learning · Computer Science 2016-11-17 Cheng Tang , Claire Monteleoni

Spherical k-means is a widely used clustering algorithm for sparse and high-dimensional data such as document vectors. While several improvements and accelerations have been introduced for the original k-means algorithm, not all easily…

Machine Learning · Computer Science 2021-11-02 Erich Schubert , Andreas Lang , Gloria Feher

We study the minimal sample size N=N(n) that suffices to estimate the covariance matrix of an n-dimensional distribution by the sample covariance matrix in the operator norm, with an arbitrary fixed accuracy. We establish the optimal bound…

Probability · Mathematics 2013-10-04 Nikhil Srivastava , Roman Vershynin

K-means plays a vital role in data mining and is the simplest and most widely used algorithm under the Euclidean Minimum Sum-of-Squares Clustering (MSSC) model. However, its performance drastically drops when applied to vast amounts of…

Machine Learning · Computer Science 2023-11-27 Rustam Mussabayev , Nenad Mladenovic , Bassem Jarboui , Ravil Mussabayev

We introduce new rounding methods to improve the accuracy of finite precision quantum arithmetic. These quantum rounding methods are applicable when multiple samples are being taken from a quantum program. We show how to use multiple…

Quantum Physics · Physics 2021-08-18 Rajiv Krishnakumar , William Zeng

We introduce a model-free relax-and-round algorithm for k-means clustering based on a semidefinite relaxation due to Peng and Wei. The algorithm interprets the SDP output as a denoised version of the original data and then rounds this…

Machine Learning · Statistics 2016-05-11 Dustin G. Mixon , Soledad Villar , Rachel Ward

We show that the popular k-means clustering algorithm (Lloyd's heuristic), used for a variety of scientific data, can result in outcomes that are unfavorable to subgroups of data (e.g., demographic groups). Such biased clusterings can have…

Machine Learning · Computer Science 2020-10-30 Mehrdad Ghadiri , Samira Samadi , Santosh Vempala

In this paper, we confirm a smoothed version of a recent conjecture on the variance of the k-fold divisor function in arithmetic progressions to individual composite moduli, in a restricted range. In contrast to a previous result of Rodgers…

Number Theory · Mathematics 2023-02-27 David T. Nguyen

A new cluster analysis method, $K$-quantiles clustering, is introduced. $K$-quantiles clustering can be computed by a simple greedy algorithm in the style of the classical Lloyd's algorithm for $K$-means. It can be applied to large and…

Methodology · Statistics 2019-11-12 Christian Hennig , Cinzia Viroli , Laura Anderlucci

We address the fundamental network design problem of constructing approximate minimum spanners. Our contributions are for the distributed setting, providing both algorithmic and hardness results. Our main hardness result shows that an…

Data Structures and Algorithms · Computer Science 2018-02-12 Keren Censor-Hillel , Michal Dory

We propose a new clustering algorithm that is robust to the presence of outliers in the dataset. We perform Lloyd-type iterations with robust estimates of the centroids. More precisely, we build on the idea of median-of-means statistics to…

Methodology · Statistics 2020-08-20 Camille Brunet-Saumard , Edouard Genetay , Adrien Saumard

In longitudinal data analysis, observation points of repeated measurements over time often vary among subjects except in well-designed experimental studies. Additionally, measurements for each subject are typically obtained at only a few…

Methodology · Statistics 2024-11-14 Michio Yamamoto , Yoshikazu Terada

We design a new algorithm for the Euclidean $k$-means problem that operates in the local model of differential privacy. Unlike in the non-private literature, differentially private algorithms for the $k$-means objective incur both additive…

Machine Learning · Computer Science 2021-06-29 Uri Stemmer

We study the problem of computing approximate minimum edge cuts by distributed algorithms. We use a standard synchronous message passing model where in each round, $O(\log n)$ bits can be transmitted over each edge (a.k.a. the CONGEST…

Data Structures and Algorithms · Computer Science 2013-11-21 Mohsen Ghaffari , Fabian Kuhn

In this paper we consider the problem of finding a maximum weight set subject to a $k$-extendible constraint in the data stream model. The only non-trivial algorithm known for this problem to date---to the best of our knowledge---is a…

Data Structures and Algorithms · Computer Science 2019-06-12 Moran Feldman , Ran Haba

$\renewcommand{\Re}{{\rm I\!\hspace{-0.025em} R}} \newcommand{\eps}{{\varepsilon}} \newcommand{\Coreset}{{\mathcal{S}}} $ In this paper, we show the existence of small coresets for the problems of computing $k$-median and $k$-means…

Computational Geometry · Computer Science 2018-10-31 Sariel Har-Peled , Soham Mazumdar

We prove asymptotic convergence for a general class of $k$-means algorithms performed over streaming data from a distribution: the centers asymptotically converge to the set of stationary points of the $k$-means cost function. To do so, we…

Machine Learning · Computer Science 2022-02-23 Sanjoy Dasgupta , Gaurav Mahajan , Geelon So

The simplex method for linear programming is known to be highly efficient in practice, and understanding its performance from a theoretical perspective is an active research topic. The framework of smoothed analysis, first introduced by…

Data Structures and Algorithms · Computer Science 2025-10-22 Sophie Huiberts , Yin Tat Lee , Xinzhi Zhang

We investigate the fine-grained complexity of approximating the classical $k$-median / $k$-means clustering problems in general metric spaces. We show how to improve the approximation factors to $(1+2/e+\varepsilon)$ and…

Data Structures and Algorithms · Computer Science 2019-04-30 Vincent Cohen-Addad , Anupam Gupta , Amit Kumar , Euiwoong Lee , Jason Li