A Convergence Theorem for the Graph Shift-type Algorithms

06/13/2013
by   Xuhui Fan, et al.
0

Graph Shift (GS) algorithms are recently focused as a promising approach for discovering dense subgraphs in noisy data. However, there are no theoretical foundations for proving the convergence of the GS Algorithm. In this paper, we propose a generic theoretical framework consisting of three key GS components: simplex of generated sequence set, monotonic and continuous objective function and closed mapping. We prove that GS algorithms with such components can be transformed to fit the Zangwill's convergence theorem, and the sequence set generated by the GS procedures always terminates at a local maximum, or at worst, contains a subsequence which converges to a local maximum of the similarity measure function. The framework is verified by expanding it to other GS-type algorithms and experimental results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/10/2014

On the Convergence of the Mean Shift Algorithm in the One-Dimensional Space

The mean shift algorithm is a non-parametric and iterative technique tha...
research
11/11/2019

Convergence to minima for the continuous version of Backtracking Gradient Descent

The main result of this paper is: Theorem. Let f:R^k→R be a C^1 funct...
research
01/14/2022

Convergence of an Asynchronous Block-Coordinate Forward-Backward Algorithm for Convex Composite Optimization

In this paper, we study the convergence properties of a randomized block...
research
09/12/2017

A convergence frame for inexact nonconvex and nonsmooth algorithms and its applications to several iterations

In this paper, we consider the convergence of an abstract inexact noncon...
research
06/22/2023

Numerical analysis of the stochastic Stefan problem

The gradient discretisation method (GDM) – a generic framework encompass...
research
11/27/2018

Counting Polynomial Roots in Isabelle/HOL: A Formal Proof of the Budan-Fourier Theorem

Many problems in computer algebra and numerical analysis can be reduced ...
research
09/03/2019

Contraction methods for continuous optimization

We describe a class of algorithms that establishes a contracting sequenc...

Please sign up or login with your details

Forgot password? Click here to reset