DeepAI AI Chat
Log In Sign Up

Almost Tight Approximation Algorithms for Explainable Clustering

by   Hossein Esfandiari, et al.

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 humans. In this paper, we study a recent framework of explainable clustering first suggested by Dasgupta et al. <cit.>. Specifically, we focus on the k-means and k-medians problems and provide nearly tight upper and lower bounds. First, we provide an O(log k loglog k)-approximation algorithm for explainable k-medians, improving on the best known algorithm of O(k) <cit.> and nearly matching the known Ω(log k) lower bound <cit.>. In addition, in low-dimensional spaces d ≪log k, we show that our algorithm also provides an O(d log^2 d)-approximate solution for explainable k-medians. This improves over the best known bound of O(d log k) for low dimensions <cit.>, and is a constant for constant dimensional spaces. To complement this, we show a nearly matching Ω(d) lower bound. Next, we study the k-means problem in this context and provide an O(k log k)-approximation algorithm for explainable k-means, improving over the O(k^2) bound of Dasgupta et al. and the O(d k log k) bound of <cit.>. To complement this we provide an almost tight Ω(k) lower bound, improving over the Ω(log k) lower bound of Dasgupta et al. Given an approximate solution to the classic k-means and k-medians, our algorithm for k-medians runs in time O(kd log^2 k ) and our algorithm for k-means runs in time O(k^2 d).


page 1

page 2

page 3

page 4


Nearly-Tight and Oblivious Algorithms for Explainable Clustering

We study the problem of explainable clustering in the setting first form...

Matrix Chain Multiplication and Polygon Triangulation Revisited and Generalized

The matrix-chain multiplication problem is a classic problem that is wid...

A Nearly Tight Analysis of Greedy k-means++

The famous k-means++ algorithm of Arthur and Vassilvitskii [SODA 2007] i...

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

We consider the problem of explainable k-medians and k-means introduced ...

Cubic upper and lower bounds for subtrajectory clustering under the continuous Fréchet distance

Detecting commuting patterns or migration patterns in movement data is a...

A Note On the Size of Largest Bins Using Placement With Linear Transformations

We study the placement of n balls into n bins where balls and bins are r...

Approximate Maximum Halfspace Discrepancy

Consider the geometric range space (X, ℋ_d) where X ⊂ℝ^d and ℋ_d is the ...