Published on Tue Dec 08 2020

Simultaneous Grouping and Denoising via Sparse Convex Wavelet Clustering

Michael Weylandt, T. Mitchell Roddenberry, Genevera I. Allen

Clustering is a ubiquitous problem in data science and signal processing. Our method is a unified, convex approach that performs both simultaneously. We demonstrate our method on synthetic examples and in an application to NMR spectroscopy.

0
0
0
Abstract

Clustering is a ubiquitous problem in data science and signal processing. In many applications where we observe noisy signals, it is common practice to first denoise the data, perhaps using wavelet denoising, and then to apply a clustering algorithm. In this paper, we develop a sparse convex wavelet clustering approach that simultaneously denoises and discovers groups. Our approach utilizes convex fusion penalties to achieve agglomeration and group-sparse penalties to denoise through sparsity in the wavelet domain. In contrast to common practice which denoises then clusters, our method is a unified, convex approach that performs both simultaneously. Our method yields denoised (wavelet-sparse) cluster centroids that both improve interpretability and data compression. We demonstrate our method on synthetic examples and in an application to NMR spectroscopy.

Wed Dec 12 2018
Machine Learning
Kernel Treelets
A new method for hierarchical clustering is presented. It combines treelets, a particular multiscale decomposition of data, with a projection on a kernel Hilbert space. The proposed approach, called kernel treelets(KT), effectively substitutes the correlation coefficient matrix.
0
0
0
Tue Mar 04 2014
Machine Learning
The Hidden Convexity of Spectral Clustering
spectral clustering has become a standard method for data analysis used in a broad range of applications. In this paper we propose a new class of algorithms for multiway spectral clustered based on optimization of acertain "contrast function" over the unit sphere.
0
0
0
Fri Jul 29 2016
Machine Learning
Data Filtering for Cluster Analysis by -Norm Regularization
A data filtering method for cluster analysis is proposed. It is based on minimizing a least squares function with a weighted -norm penalty. The method also exploits a suitable technique to choose the penalty parameter.
0
0
0
Wed Nov 02 2011
Machine Learning
Revisiting k-means: New Algorithms via Bayesian Nonparametrics
Bayesian nonparametrics can be used for modeling infinite mixtures, and hierarchical Bayesian models can be utilized for sharing clusters. For the most part, such flexibility is lacking in classical clustering methods such as k-means.
0
0
0
Mon Jan 18 2016
Machine Learning
Sparse Convex Clustering
Convex clustering is a relaxation of k-means clustering and hierarchical clustering. The key idea is to formulate conveX clustering in a form of regularization. We demonstrate that the performance of convex clusters could be distorted when uninformative features are included.
0
0
0
Sun Oct 18 2015
Machine Learning
Clustering Noisy Signals with Structured Sparsity Using Time-Frequency Representation
We propose a simple and efficient time-series clustering framework particularly suited for low Signal-to-Noise Ratio (SNR) We extend the sparse K-means algorithm by incorporating structured sparsity, and use it to exploit the multi-scale property of wavelets and group
0
0
0