Stochastic Mean-Shift Clustering

TL;DR

This paper introduces a stochastic mean-shift clustering algorithm that improves upon the standard method, demonstrating better performance on synthetic data and practical speaker clustering applications.

Contribution

The paper proposes a novel stochastic mean-shift algorithm with convergence guarantees, enhancing clustering performance over traditional methods.

Findings

Outperforms standard mean-shift in most cases

Shows effective convergence on Gaussian mixture data

Successfully applied to speaker clustering

Abstract

We present a stochastic version of the mean-shift clustering algorithm. In this stochastic version a randomly chosen sequence of data points move according to partial gradient ascent steps of the objective function. Theoretical results illustrating the convergence of the proposed approach, and its relative performances is evaluated on synthesized 2-dimensional samples generated by a Gaussian mixture distribution and compared with state-of-the-art methods. It can be observed that in most cases the stochastic mean-shift clustering outperforms the standard mean-shift. We also illustrate as a practical application the use of the presented method for speaker clustering.