On identifying clusters from sum-of-norms clustering computation

06/19/2020
by   Tao Jiang, et al.
0

Sum-of-norms clustering is a clustering formulation based on convex optimization that automatically induces hierarchy. Multiple algorithms have been proposed to solve the optimization problem: subgradient descent by Hocking et al. <cit.>, ADMM and ADA by Chi and Lange <cit.>, stochastic incremental algorithm by Panahi et al. <cit.> and semismooth Newton-CG augmented Lagrangian method by Yuan et al. <cit.>. All algorithms yield approximate solutions, even though an exact solution is demanded to determine the correct cluster assignment. The purpose of this paper is to close the gap between the output from existing algorithms and the exact solution to the optimization problem. We present a clustering test which identifies and certifies the correct cluster assignment from an approximate solution yielded by any primal-dual algorithm. The test may not succeed if the approximation is inaccurate. However, we show the correct cluster assignment is guaranteed to be found by a symmetric primal-dual path following algorithm after sufficiently many iterations, provided that the model parameter λ avoids a finite number of bad values. Numerical experiments are implemented to support our results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/19/2019

Recovery of a mixture of Gaussians by sum-of-norms clustering

Sum-of-norms clustering is a method for assigning n points in R^d to K c...
research
04/14/2022

Numerical evaluation of dual norms via the MM algorithm

We deal with the problem of numerically computing the dual norm, which i...
research
10/04/2018

Convex Clustering: Model, Theoretical Guarantee and Efficient Algorithm

Clustering is a fundamental problem in unsupervised learning. Popular me...
research
09/20/2021

Local versions of sum-of-norms clustering

Sum-of-norms clustering is a convex optimization problem whose solution ...
research
01/23/2023

Augmented Block-Arnoldi Recycling CFD Solvers

One of the limitations of recycled GCRO methods is the large amount of c...
research
11/11/2019

Revisiting the Approximate Carathéodory Problem via the Frank-Wolfe Algorithm

The approximate Carathéodory theorem states that given a polytope P, eac...
research
05/11/2021

A Euclidean Distance Matrix Model for Convex Clustering

Clustering has been one of the most basic and essential problems in unsu...

Please sign up or login with your details

Forgot password? Click here to reset