paper-with-me

홈 › Papers

Near-optimal Algorithms for Explainable k-Medians and k-Means

2021-07-02 · Konstantin Makarychev, Liren Shan

We consider the problem of explainable $k$-medians and $k$-means introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian~(ICML 2020). In this problem, our goal is to find a threshold decision tree that partitions data into $k$ clusters and minimizes the $k$-medians or $k$-means objective. The obtained clustering is easy to interpret because every decision node of a threshold tree splits data based on a single feature into two groups. We propose a new algorithm for this problem which is $\tilde O(\log k)$ competitive with $k$-medians with $\ell_1$ norm and $\tilde O(k)$ competitive with $k$-means. This is an improvement over the previous guarantees of $O(k)$ and $O(k^2)$ by Dasgupta et al (2020). We also provide a new algorithm which is $O(\log^{3/2} k)$ competitive for $k$-medians with $\ell_2$ norm. Our first algorithm is near-optimal: Dasgupta et al (2020) showed a lower bound of $\Omega(\log k)$ for $k$-medians; in this work, we prove a lower bound of $\tilde\Omega(k)$ for $k$-means. We also provide a lower bound of $\Omega(\log k)$ for $k$-medians with $\ell_2$ norm.

📄 PDF Abstract BibTeX arXiv:2107.00798

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Explainable k-Means and k-Medians Clustering

2020-01-01 · ICML 2020 1 · Michal Moshkovitz, Sanjoy Dasgupta, Cyrus Rashtchian, Nave Frost

Clustering is a popular unsupervised learning method for geometric data. Unfortunately, many clustering algorithms use global properties of the data, and there are no simple explanations for cluster assignments. To impro…

Clustering

Explainable $k$-Means and $k$-Medians Clustering

2020-02-28 · Sanjoy Dasgupta, Nave Frost, Michal Moshkovitz, Cyrus Rashtchian

Clustering is a popular form of unsupervised learning for geometric data. Unfortunately, many clustering algorithms lead to cluster assignments that are hard to explain, partially because they depend on all the features …

Clustering

Almost Tight Approximation Algorithms for Explainable Clustering

2021-07-01 · Hossein Esfandiari, Vahab Mirrokni, Shyam Narayanan

Recently, due to an increasing interest for transparency in artificial intelligence, several methods of explainable machine learning have been developed with the simultaneous goal of accuracy and interpretability by huma…

Clustering

Nearly-Tight and Oblivious Algorithms for Explainable Clustering

2021-06-30 · NeurIPS 2021 12 · Buddhima Gamlath, Xinrui Jia, Adam Polak, Ola Svensson

We study the problem of explainable clustering in the setting first formalized by Dasgupta, Frost, Moshkovitz, and Rashtchian (ICML 2020). A $k$-clustering is said to be explainable if it is given by a decision tree wher…

Clustering

Dynamic Algorithm for Explainable k-medians Clustering under lp Norm

2025-12-01 · Konstantin Makarychev, Ilias Papanikolaou, Liren Shan arxiv

We study the problem of explainable k-medians clustering introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian (2020). In this problem, the goal is to construct a threshold decision tree that partitions data into k c…