Low-rank optimization for distance matrix completion

This paper addresses the problem of low-rank distance matrix completion. This problem amounts to recover the missing entries of a distance matrix when the dimension of the data embedding space is possibly unknown but small compared to the number of considered data points. The focus is on high-dimensional problems. We recast the considered problem into an optimization problem over the set of low-rank positive semidefinite matrices and propose two efficient algorithms for low-rank distance matrix completion. In addition, we propose a strategy to determine the dimension of the embedding space. The resulting algorithms scale to high-dimensional problems and monotonically converge to a global solution of the problem. Finally, numerical experiments illustrate the good performance of the proposed algorithms on benchmarks. © 2011 IEEE.

Optimization Algorithms on Matrix Manifolds

This book shows how to exploit the special structure of such problems to develop efficient numerical algorithms.

Determination of the rheological parameters of self-compacting concrete matrix using slump flow test

The classification of a concrete mixture as self-compacting (SCC) is performed by a series of empirical characterization tests that have been designed to assess not only the flowability of the mixture but also its segregation resistance and filling ability. The objective of the present work is to correlate the rheological parameters of SCC matrix, yield stress and plastic viscosity, to slump flow measurements. The focus of the slump flow test investigation was centered on the fully yielded flow regime and an empirical model relating the yield stress to material and flow parameters is proposed. Our experimental data revealed that the time for a spread of 500 mm which is used in engineering practice as reference for measurement parameters, is an arbitrary choice. Our findings indicate that the non-dimensional final spread is linearly related to the non-dimensional yield-stress. Finally, there are strong indications that the non-dimensional viscosity of the mixture is associated with the non-dimensional final spread as well as the stopping time of the slump flow; this experimental data set suggests an exponential decay of the final spread and stopping time with viscosity. © Appl. Rheol.

Dynamics of filopodium-like protrusion and endothelial cellular motility on onedimensional extracellular matrix fibrils

Endothelial filopodia play key roles in guiding the tubular sprouting during angiogenesis. However, their dynamic morphological characteristics, with the associated implications in cell motility, have been subjected to limited investigations. In this work, the interaction between endothelial cells and extracellular matrix fibrils was recapitulated in vitro, where a specific focus was paid to derive the key morphological parameters to define the dynamics of filopodium-like protrusion during cell motility. Based on one-dimensional gelatin fibrils patterned by near-field electrospinning (NFES), we study the response of endothelial cells (EA.hy926) under normal culture or ROCK inhibition. It is shown that the behaviour of temporal protrusion length versus cell motility can be divided into distinct modes. Persistent migration was found to be one of the modes which permitted cell displacement for over 300 μm at a speed of approximately 1 μm min-1. ROCK inhibition resulted in abnormally long protrusions and diminished the persistent migration, but dramatically increased the speeds of protrusion extension and retraction. Finally, we also report the breakage of protrusion during cell motility, and examine its phenotypic behaviours. © 2014 The Author(s) Published by the Royal Society. All rights reserved.

Fixed-rank matrix factorizations and Riemannian low-rank optimization

Motivated by the problem of learning a linear regression model whose parameter is a large fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function defined on the set of fixed-rank matrices. We adopt the geometric framework of optimization on Riemannian quotient manifolds. We study the underlying geometries of several well-known fixed-rank matrix factorizations and then exploit the Riemannian quotient geometry of the search space in the design of a class of gradient descent and trust-region algorithms. The proposed algorithms generalize our previous results on fixed-rank symmetric positive semidefinite matrices, apply to a broad range of applications, scale to high-dimensional problems, and confer a geometric basis to recent contributions on the learning of fixed-rank non-symmetric matrices. We make connections with existing algorithms in the context of low-rank matrix completion and discuss the usefulness of the proposed framework. Numerical experiments suggest that the proposed algorithms compete with state-of-the-art algorithms and that manifold optimization offers an effective and versatile framework for the design of machine learning algorithms that learn a fixed-rank matrix. © 2013 Springer-Verlag Berlin Heidelberg.