A Caltech Library Service

A Riemannian Approach for Graph-Based Clustering by Doubly Stochastic Matrices

Douik, Ahmed and Hassibi, Babak (2018) A Riemannian Approach for Graph-Based Clustering by Doubly Stochastic Matrices. In: 2018 IEEE Statistical Signal Processing Workshop (SSP). IEEE , Piscataway, NJ, pp. 806-810. ISBN 978-1-5386-1571-3.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


Convex optimization is a well-established area with applications in almost all fields. However, these convex methods can be rather slow and computationally intensive for high dimensional problems. For a particular class of problems, this paper considers a different approach, namely Riemannian optimization. The main idea is to view the constrained optimization problem as an unconstrained one over a restricted search space (the manifold). Riemannian optimization explicitly exploits the geometry of the problem and often reduces its dimension, thereby potentially allowing significant speedup as compared to conventional approaches. The paper introduces the doubly stochastic, the symmetric, and the definite multinomial manifolds which generalize the simplex. The method is applied to a convex and a non-convex graph-based clustering problem. Theoretical analysis and simulation results demonstrate the efficiency of the proposed method over the state of the art as it outperforms conventional generic and specialized solvers, especially in high dimensions.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Douik, Ahmed0000-0001-7791-9443
Additional Information:© 2018 IEEE.
Subject Keywords:Riemannian optimization, manifold geometry, doubly stochastic matrices, symmetric matrices, convex optimization
Record Number:CaltechAUTHORS:20180906-141856985
Persistent URL:
Official Citation:A. Douik and B. Hassibi, "A Riemannian Approach for Graph-Based Clustering by Doubly Stochastic Matrices," 2018 IEEE Statistical Signal Processing Workshop (SSP), Freiburg im Breisgau, Germany, 2018, pp. 806-810. doi: 10.1109/SSP.2018.8450685
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:89426
Deposited By: Tony Diaz
Deposited On:07 Sep 2018 00:13
Last Modified:16 Nov 2021 00:35

Repository Staff Only: item control page