Searcharxiv⌕ Search

arXiv subjects

Thomas Laurent

Publications and source records attributed to Thomas Laurent.

46 records · Page 3Linked to original sources

Enhanced Lasso Recovery on Graph

This work aims at recovering signals that are sparse on graphs. Compressed sensing offers techniques for signal recovery from a few linear measurements and graph Fourier analysis provides a signal representation on graph. In this paper, we leverage these two frameworks to introduce a new Lasso recovery algorithm on graphs. More precisely, we present a non-convex, non-smooth algorithm that outperforms the standard convex Lasso technique. We carry out numerical experiments on three benchmark graph datasets.

cs.LG↗

Consistency of Cheeger and Ratio Graph Cuts

This paper establishes the consistency of a family of graph-cut-based algorithms for clustering of data clouds. We consider point clouds obtained as samples of a ground-truth measure. We investigate approaches to clustering based on minimizing objective functionals defined on proximity graphs of the given sample. Our focus is on functionals based on graph cuts like the Cheeger and ratio cuts. We show that minimizers of the these cuts converge as the sample size increases to a minimizer of a corresponding continuum cut (which partitions the ground truth measure). Moreover, we obtain sharp conditions on how the connectivity radius can be scaled with respect to the number of sample points for the consistency to hold. We provide results for two-way and for multiway cuts. Furthermore we provide numerical experiments that illustrate the results and explore the optimality of scaling in dimension two.

stat.ML↗

An Incremental Reseeding Strategy for Clustering

In this work we propose a simple and easily parallelizable algorithm for multiway graph partitioning. The algorithm alternates between three basic components: diffusing seed vertices over the graph, thresholding the diffused seeds, and then randomly reseeding the thresholded clusters. We demonstrate experimentally that the proper combination of these ingredients leads to an algorithm that achieves state-of-the-art performance in terms of cluster purity on standard benchmarks datasets. Moreover, the algorithm runs an order of magnitude faster than the other algorithms that achieve comparable results in terms of accuracy. We also describe a coarsen, cluster and refine approach similar to GRACLUS and METIS that removes an additional order of magnitude from the runtime of our algorithm while still maintaining competitive accuracy.

stat.ML↗

Multiclass Total Variation Clustering

Ideas from the image processing literature have recently motivated a new set of clustering algorithms that rely on the concept of total variation. While these algorithms perform well for bi-partitioning tasks, their recursive extensions yield unimpressive results for multiclass clustering tasks. This paper presents a general framework for multiclass total variation clustering that does not rely on recursion. The results greatly outperform previous total variation algorithms and compare well with state-of-the-art NMF approaches.

stat.ML↗

A Method Based on Total Variation for Network Modularity Optimization using the MBO Scheme

The study of network structure is pervasive in sociology, biology, computer science, and many other disciplines. One of the most important areas of network science is the algorithmic detection of cohesive groups of nodes called "communities". One popular approach to find communities is to maximize a quality function known as {\em modularity} to achieve some sort of optimal clustering of nodes. In this paper, we interpret the modularity function from a novel perspective: we reformulate modularity optimization as a minimization problem of an energy functional that consists of a total variation term and an $\ell_2$ balance term. By employing numerical techniques from image processing and $\ell_1$ compressive sensing -- such as convex splitting and the Merriman-Bence-Osher (MBO) scheme -- we develop a variational algorithm for the minimization problem. We present our computational results using both synthetic benchmark networks and real data.

cs.SI↗

An Adaptive Total Variation Algorithm for Computing the Balanced Cut of a Graph

We propose an adaptive version of the total variation algorithm proposed in [3] for computing the balanced cut of a graph. The algorithm from [3] used a sequence of inner total variation minimizations to guarantee descent of the balanced cut energy as well as convergence of the algorithm. In practice the total variation minimization step is never solved exactly. Instead, an accuracy parameter is specified and the total variation minimization terminates once this level of accuracy is reached. The choice of this parameter can vastly impact both the computational time of the overall algorithm as well as the accuracy of the result. Moreover, since the total variation minimization step is not solved exactly, the algorithm is not guarantied to be monotonic. In the present work we introduce a new adaptive stopping condition for the total variation minimization that guarantees monotonicity. This results in an algorithm that is actually monotonic in practice and is also significantly faster than previous, non-adaptive algorithms.

math.OC↗

Convergence of a Steepest Descent Algorithm for Ratio Cut Clustering

Unsupervised clustering of scattered, noisy and high-dimensional data points is an important and difficult problem. Tight continuous relaxations of balanced cut problems have recently been shown to provide excellent clustering results. In this paper, we present an explicit-implicit gradient flow scheme for the relaxed ratio cut problem, and prove that the algorithm converges to a critical point of the energy. We also show the efficiency of the proposed algorithm on the two moons dataset.

math.OC↗

Characterization of radially symmetric finite time blowup in multidimensional aggregation equations,

This paper studies the transport of a mass $μ$ in $\real^d, d \geq 2,$ by a flow field $v= -\nabla K*μ$. We focus on kernels $K=|x|^α/ α$ for $2-d\leq α<2$ for which the smooth densities are known to develop singularities in finite time. For this range This paper studies the transport of a mass $μ$ in $\real^d, d \geq 2,$ by a flow field $v= -\nabla K*μ$. We focus on kernels $K=|x|^α/ α$ for $2-d\leq α<2$ for which the smooth densities are known to develop singularities in finite time. For this range we prove the existence for all time of radially symmetric measure solutions that are monotone decreasing as a function of the radius, thus allowing for continuation of the solution past the blowup time. The monotone constraint on the data is consistent with the typical blowup profiles observed in recent numerical studies of these singularities. We prove monotonicity is preserved for all time, even after blowup, in contrast to the case $α>2$ where radially symmetric solutions are known to lose monotonicity. In the case of the Newtonian potential ($α=2-d$), under the assumption of radial symmetry the equation can be transformed into the inviscid Burgers equation on a half line. This enables us to prove preservation of monotonicity using the classical theory of conservation laws. In the case $2 -d < α< 2$ and at the critical exponent $p$ we exhibit initial data in $L^p$ for which the solution immediately develops a Dirac mass singularity. This extends recent work on the local ill-posedness of solutions at the critical exponent.

math.AP↗

The Planar Optics Phase Sensor: a study for the VLTI 2nd Generation Fringe Tracker

In a few years, the second generation instruments of the Very Large Telescope Interferometer (VLTI) will routinely provide observations with 4 to 6 telescopes simultaneously. To reach their ultimate performance, they will need a fringe sensor capable to measure in real time the randomly varying optical paths differences. A collaboration between LAOG (PI institute), IAGL, OCA and GIPSA-Lab has proposed the Planar Optics Phase Sensor concept to ESO for the 2nd Generation Fringe Tracker. This concept is based on the integrated optics technologies, enabling the conception of extremely compact interferometric instruments naturally providing single-mode spatial filtering. It allows operations with 4 and 6 telescopes by measuring the fringes position thanks to a spectrally dispersed ABCD method. We present here the main analysis which led to the current concept as well as the expected on-sky performance and the proposed design.

astro-ph.IM↗

Tests of achromatic phase shifters performed on the SYNAPSE test bench: a progress report

The achromatic phase shifter (APS) is a component of the Bracewell nulling interferometer studied in preparation for future space missions (viz. Darwin/TPF-I) focusing on spectroscopic study of Earth-like exo-planets. Several possible designs of such an optical subsystem exist. Four approaches were selected for further study. Thales Alenia Space developed a dielectric prism APS. A focus crossing APS prototype was developed by the OCA, Nice, France. A field reversal APS prototype was prepared by the MPIA in Heidelberg, Germany. Centre Spatial de Liège develops a concept based on Fresnel's rhombs. This paper presents a progress report on the current work aiming at evaluating these prototypes on the SYNAPSE test bench at the Institut d'Astrophysique Spatiale in Orsay, France.

astro-ph↗