
The functional meanshift algorithm for mode hunting and clustering in infinite dimensions
We introduce the functional meanshift algorithm, an iterative algorithm...
read it

Kernel Smoothing, Mean Shift, and Their Learning Theory with Directional Data
Directional data consist of observations distributed on a (hyper)sphere,...
read it

On the Convergence of the Mean Shift Algorithm in the OneDimensional Space
The mean shift algorithm is a nonparametric and iterative technique tha...
read it

On Convergence of Epanechnikov Mean Shift
Epanechnikov Mean Shift is a simple yet empirically very effective algor...
read it

Finding Modes by Probabilistic Hypergraphs Shifting
In this paper, we develop a novel paradigm, namely hypergraph shift, to ...
read it

Scalable Laplacian Kmodes
We advocate Laplacian Kmodes for joint clustering and density mode find...
read it

Error Bounds for Piecewise Smooth and Switching Regression
The paper deals with regression problems, in which the nonsmooth target ...
read it
Space Partitioning and Regression Mode Seeking via a MeanShiftInspired Algorithm
The mean shift (MS) algorithm is a nonparametric method used to cluster sample points and find the local modes of kernel density estimates, using an idea based on iterative gradient ascent. In this paper we develop a meanshiftinspired algorithm to estimate the modes of regression functions and partition the sample points in the input space. We prove convergence of the sequences generated by the algorithm and derive the nonasymptotic rates of convergence of the estimated local modes for the underlying regression model. We also demonstrate the utility of the algorithm for dataenabled discovery through an application on biomolecular structure data. An extension to subspace constrained mean shift (SCMS) algorithm used to extract ridges of regression functions is briefly discussed.
READ FULL TEXT
Comments
There are no comments yet.