English
Related papers

Related papers: Recovery guarantees for exemplar-based clustering

200 papers

$k$-means and $k$-median clustering are powerful unsupervised machine learning techniques. However, due to complicated dependences on all the features, it is challenging to interpret the resulting cluster assignments. Moshkovitz, Dasgupta,…

Data Structures and Algorithms · Computer Science 2021-12-17 Sayan Bandyapadhyay , Fedor V. Fomin , Petr A. Golovach , William Lochet , Nidhi Purohit , Kirill Simonov

Motivation: Public and private repositories of experimental data are growing to sizes that require dedicated methods for finding relevant data. To improve on the state of the art of keyword searches from annotations, methods for…

Machine Learning · Statistics 2016-01-08 Paul Blomstedt , Ritabrata Dutta , Sohan Seth , Alvis Brazma , Samuel Kaski

We study an active cluster recovery problem where, given a set of $n$ points and an oracle answering queries like "are these two points in the same cluster?", the task is to recover exactly all clusters using as few queries as possible. We…

Machine Learning · Computer Science 2021-06-10 Marco Bressan , Nicolò Cesa-Bianchi , Silvio Lattanzi , Andrea Paudice

$\renewcommand{\Re}{\mathbb{R}}$Given a set $P$ of $n$ points in $\Re^d$, consider the problem of computing $k$ subsets of $P$ that form clusters that are well-separated from each other, and each of them is large (cardinality wise). We…

Computational Geometry · Computer Science 2021-06-11 Sariel Har-Peled , Joseph Rogge

The problem of constrained clustering has attracted significant attention in the past decades. In this paper, we study the balanced $k$-center, $k$-median, and $k$-means clustering problems where the size of each cluster is constrained by…

Computational Geometry · Computer Science 2018-09-11 Hu Ding

We consider the problem of clustering with the longest-leg path distance (LLPD) metric, which is informative for elongated and irregularly shaped clusters. We prove finite-sample guarantees on the performance of clustering with respect to…

Machine Learning · Statistics 2019-03-07 Anna Little , Mauro Maggioni , James M. Murphy

This paper studies high-dimensional sparse clustering, a combinatorial NP-hard problem arising from the bilinear coupling between cluster assignment and feature selection. We analyze semidefinite programming (SDP) relaxations of $K$-means…

Methodology · Statistics 2026-02-17 Jongmin Mun , Paromita Dubey , Yingying Fan

Clustering is a fundamental problem in many areas, which aims to partition a given data set into groups based on some distance measure, such that the data points in the same group are similar while that in different groups are dissimilar.…

Neural and Evolutionary Computing · Computer Science 2023-07-25 Chao Qian

In this paper we formulate in general terms an approach to prove strong consistency of the Empirical Risk Minimisation inductive principle applied to the prototype or distance based clustering. This approach was motivated by the Divisive…

Machine Learning · Statistics 2010-04-20 Vladimir Nikulin , Geoffrey J. McLachlan

Probabilistic clustering models (or equivalently, mixture models) are basic building blocks in countless statistical models and involve latent random variables over discrete spaces. For these models, posterior inference methods can be…

Machine Learning · Statistics 2020-06-24 Ari Pakman , Yueqi Wang , Catalin Mitelut , JinHyung Lee , Liam Paninski

$k$-means clustering is a well-studied problem due to its wide applicability. Unfortunately, there exist strong theoretical limits on the performance of any algorithm for the $k$-means problem on worst-case inputs. To overcome this barrier,…

Machine Learning · Computer Science 2022-03-22 Jon C. Ergun , Zhili Feng , Sandeep Silwal , David P. Woodruff , Samson Zhou

Econometric applications with multi-way clustering often feature a small number of effective clusters or heavy-tailed data, making standard cluster-robust and bootstrap inference unreliable in finite samples. In this paper, we develop a…

Methodology · Statistics 2026-01-14 Wenxuan Guo , Panos Toulis , Yuhao Wang

We consider the classical $k$-means clustering problem in the setting bi-criteria approximation, in which an algoithm is allowed to output $\beta k > k$ clusters, and must produce a clustering with cost at most $\alpha$ times the to the…

Data Structures and Algorithms · Computer Science 2015-08-04 Konstantin Makarychev , Yury Makarychev , Maxim Sviridenko , Justin Ward

We consider the sampling of the coupled cluster expansion within stochastic coupled cluster theory. Observing the limitations of previous approaches due to the inherently non-linear behaviour of a coupled cluster wavefunction representation…

Chemical Physics · Physics 2018-08-14 Charles J. C. Scott , Alex J. W. Thom

Given a set of data, one central goal is to group them into clusters based on some notion of similarity between the individual objects. One of the most popular and widely-used approaches is k-means despite the computational hardness to find…

Optimization and Control · Mathematics 2018-07-24 Xiaodong Li , Yang Li , Shuyang Ling , Thomas Strohmer , Ke Wei

In the mixture models problem it is assumed that there are $K$ distributions $\theta_{1},\ldots,\theta_{K}$ and one gets to observe a sample from a mixture of these distributions with unknown coefficients. The goal is to associate instances…

Machine Learning · Statistics 2013-12-02 Jason D Lee , Ran Gilad-Bachrach , Rich Caruana

Clustering is one of the widely used techniques to find out patterns from a dataset that can be applied in different applications or analyses. K-means, the most popular and simple clustering algorithm, might get trapped into local minima if…

Machine Learning · Computer Science 2022-10-19 Zillur Rahman , Md. Sabir Hossain , Mohammad Hasan , Ahmed Imteaj

Given two sets of points $A$ and $B$ in a normed plane, we prove that there are two linearly separable sets $A'$ and $B'$ such that $\mathrm{diam}(A')\leq \mathrm{diam}(A)$, $\mathrm{diam}(B')\leq \mathrm{diam}(B)$, and $A'\cup B'=A\cup B.$…

Computational Geometry · Computer Science 2017-09-18 Pedro Martín , Diego Yáñez

Recovery procedures in various application in Data Science are based on \emph{stable point separation}. In its simplest form, stable point separation implies that if $f$ is "far away" from $0$, and one is given a random sample…

Probability · Mathematics 2019-04-19 Shahar Mendelson , Grigoris Paouris

Classical multidimensional scaling is an important dimension reduction technique. Yet few theoretical results characterizing its statistical performance exist. This paper provides a theoretical framework for analyzing the quality of…

Statistics Theory · Mathematics 2020-07-09 Anna Little , Yuying Xie , Qiang Sun