S³ seminar :Décomposition spectroscopique en imagerie multispectrale

Seminar on April 06, 2018, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Vincent MAZET and Hassan MORTADA (ICube / équipe IMAGeS / groupe IPSEO, Université de Strasbourg)


La cinématique interne des galaxies est une clé pour comprendre l'histoire de l'Univers. Elle peut être étudiée en analysant les raies du spectre de la galaxie qui sont décalées par effet Doppler. Les observations multispectrales des galaxies permettent donc de mesurer le décalage des raies dans chaque pixel. Par ailleurs, la spectroscopie de photoélectrons est une technologie qui permet de suivre l'état d'un système en fonction du temps. Les données produites sont une séquences de spectres dont les raies évoluent au cours des acquisitions. Ces deux applications ont en commun des signaux spectroscopiques, répartis dans l'espace ou le temps, et dont les raies évoluent lentement en longueur d'onde, en intensité et en forme.

Un grand nombre de travaux portent sur la décomposition d'un unique spectre, mais aucune approche ne permet la décomposition simultanée de plusieurs spectres présentant une évolution lente des raies. Le projet DSIM, financé par l'ANR, a permis de développer des outils pour décomposer ces spectres, c'est-à-dire pour estimer le nombre et les paramètres des raies dans les spectres. La décomposition spectroscopique est considérée comme un problème inverse : les raies sont modélisées par une fonction paramétrique dont les paramètres sont à estimer.

Nous avons principalement exploré deux manières d'introduire et de traiter l'information d'évolution lente de ces paramètres. D'une part, le problème a été établi dans le cadre bayésien et l'utilisation de l'algorithme RJMCMC a permis d'obtenir de très bon résultats. D'autre part, afin accélérer le temps de calcul de cette première méthode, nous avons considéré le problème comme une séparation de sources retardées et paramétriques. Le défi réside dans le fait que les sources sont extrêmement corrélées. Un schéma de moindres carrés alternés incluant un algorithme d'approximation parcimonieuse a pour cela été conçu.

Biography: Vincent Mazet a soutenu sa thèse à l'Université de Nancy en 2005. Depuis 2006, il est maître de conférences à l'Université de Strasbourg et effectue ses recherches dans le laboratoire ICube. Ses recherches portent sur les problèmes inverses en traitement d'images, en utilisant en particulier des approches bayésiennes ou par approximation parcimonieuse, et en les appliquant à la spectroscopie, à la télédétection ou à l'imagerie hyperspectrale astronomique.

Hassan Mortada a eu son licence en électronique à l’Université Libanaise (UL) en  2013. Il a obtenu son master en 2015 à l’Université de Brest (master recherche signaux et circuits).  Depuis 2015, il prépare sa thèse à l’Université de Strasbourg, ICUBE. Ses thématiques de recherche concernent les problèmes inverses et l'approximation parcimonieuse appliquée aux données spectroscopiques.

S³ seminar : Chauves-souris, écholocation et neuroscience computationnelle : que nous disent les bornes de Cramer-Rao ?

Seminar on March 09, 2018, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle des séminaires du L2S
Didier MAUUARY (BLUEBAT)


L’écholocation chez les mammifères, découverte dans les années 50, n’a pas fini de nous surprendre. L’intérêt pour la discipline, qu’on aborde désormais sur l’angle du sonar/radar cognitif (coté traitement du signal et ingénierie système) ou des neurosciences computationnelles (du côté des biologistes, éthologues ou des neurosciences) semble au contraire connaitre un regain d’intérêt ces dernières années, notamment dans une perspective bayésienne.

Nous montrons dans cet exposé des résultats récents obtenus lors de la mise au point d’un des premiers systèmes opérationnels de géolocalisation acoustique dynamique de l’animal dans son environnement naturel. Dans ce travail, nous exploitons en premier lieu la théorie de Fischer et les célèbres bornes de Cramer-Rao pour affronter, d’une part, la problématique de l’incertitude temps-fréquence intrinsèque aux formes d’onde émises par l’animal et, d’autre part, analyser la problématique de l’adaptation de son système sonar en fonction de l’objectif de perception et des contraintes environnementales.

Ces travaux reprennent les premières tentatives de trajectographie acoustique passive de l’animal par Yves Tupinier et Patrick Flandrin, il y a une quarantaine d’année. Ils dévoilent désormais des résultats concrets particulièrement novateurs sur le plan biologique, comportemental et/ou neurologique. Par ailleurs, la portée industrielle de ces travaux est stratégique à l’heure où nous cherchons désormais à développer des systèmes de drone capable de voler en milieu confiné, ce que la chauve-souris sait faire admirablement, les yeux fermés…

Biography: Didier Mauuary, Ingénieur Centrale Paris (89), spécialité physique de l’océan et de l’atmosphère et Docteur INPG (94) débute ses travaux en acoustique sous-marine pour développer des méthodes d’observation physique globale à l’échelle climatique. Il poursuit ses travaux de recherche en collaboration avec l’université Carnegie Mellon de Pittsburgh et l’institut des sciences de la Mer de Kiel, ce qui l’amène à cosigner un article dans le magazine Nature. Il poursuit ensuite sa carrière dans l’industrie du SONAR, principalement dans le secteur de la Défense et publie une dizaine d’articles scientifiques dans les revues et conférences internationales. Il crée en 2010 la première startup française dont le programme de R&D est principalement axé sur la chauve-souris.

S³ seminar : Fourier transforms of polytopes and their role in Number Theory and Combinatorics

Seminar on December 21, 2017, 11:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Sinai Robins, (University of Sao Paulo, Sao Paulo, Brasil and Brown University, Providence, USA)


We introduce the topic of the Fourier transform of a Euclidean polytope, first by examples and then by more general formulations.  Then we point out how we can use this transform (and the frequency space) to analyze the following problems:
1.  Compute lattice point enumeration formulas for polytopes
2.  Relate the transforms of polytopes to tilings of Euclidean space by translations of a polytope

We will give a flavor of how such applications arise, and we point to some conjectures and applications.

S³ seminar : On the polynomial part of a restricted partition function

Seminar on December 21, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Karl Dilcher, (Dalhousie University, Halifax, Canada)


We prove an explicit formula for the polynomial part of a restricted
partition function, also known as the first Sylvester wave. This is achieved by way of some identities for higher-order Bernoulli polynomials, one of which is analogous to Raabe's well-known multiplication formula for the ordinary Bernoulli polynomials. As a consequence of our main result we obtain an asymptotic expression of the first Sylvester wave as the coefficients of the restricted partition grow arbitrarily large.
(Joint work with Christophe Vignat).

S³ seminar : A Random Block-Coordinate Douglas-Rachford Splitting Method with Low Computational Complexity for Binary Logistic Regression

Seminar on November 24, 2017, 2:00 PM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Émilie Chouzenoux (CVN, CentraleSupélec/INRIA, Université Paris-Est Marne-La-Vallée)


In this talk, I will present a new optimization algorithm for sparse logistic regression based on a stochastic version of the Douglas-Rachford splitting method. The algorithm sweeps the training set by randomly selecting a mini-batch of data at each iteration, and it allows us to update the variables in a block coordinate manner. Our approach leverages the proximity operator of the logistic loss, which is expressed with the generalized Lambert W function. Experiments carried out on standard datasets demonstrate the efficiency of our approach w.r.t. stochastic gradient-like methods. (joint work with Luis M. Briceño-Arias, Afef Cherni, Giovanni Chierchia and Jean-Christophe Pesquet)

S³: Estimation de l’intensité d’un processus de comptage en grande dimension

Seminar on November 17, 2017, 2:00 PM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Sarah Lemler (MICS, CentraleSupélec, Gif)


Nous cherchons à estimer/apprendre le lien entre des covariables en grande dimension et l’intensité
avec laquelle des événements se produisent (décès, crises d’asthme, achats, notes de blogs, sinistres...).

Pour répondre à cette problématique, nous proposons deux approches pour estimer l’intensité
de sauts d’un processus de comptage en présence d’un grand nombre de covariables. D’abord, nous
considérons une intensité non-paramétrique et nous l’estimons par le meilleur modèle de Cox. Nous
considérons alors une procédure Lasso, spécifique à la grande dimension, pour estimer simultanément
les deux paramètres inconnus du meilleur modèle de Cox approximant l’intensité. Nous prouvons
des inégalités oracles non-asymptotiques pour l’estimateur Lasso obtenu.

Dans une seconde partie, nous supposons que l’intensité satisfait un modèle de Cox. Nous proposons
deux procédures en deux étapes pour estimer les paramètres inconnus du modèle de Cox. La
première étape est commune aux deux procédures, il s’agit d’estimer le paramètre de régression en
grande dimension via une procédure Lasso. Le risque de base est ensuite estimé soit par sélection de
modèles, soit par un estimateur à noyau avec une fenêtre choisie par la méthode de Goldenshluger
et Lepski. Nous établissons des inégalités oracles non-asymptotiques pour les deux estimateurs du
risque de base ainsi obtenus. Nous menons une étude comparative de ces estimateurs sur des données
simulées, et enfin, nous appliquons les procédures implémentées à une base de données sur le cancer
du sein.

S³: Selective Updating and Cooperation for Distributed Estimation and Detection

Seminar on October 26, 2017, 2:00 PM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Marcello Campos (COPPE/UFRJ)


This talk discusses selective update and cooperation strategies for parameter estimation and event detection in distributed adaptive sensor networks. We investigate a set-membership filtering approach which results in reduced complexity for updating parameter estimates at each network node. We explore cooperation strategies in adaptive distributed sensor networks for reduction in information exchange between cooperating nodes, and search for an optimal strategy to obtain consensus estimates.

Bio: This talk discusses selective update and cooperation strategies for parameter estimation and event detection in distributed adaptive sensor networks. We investigate a set-membership filtering approach which results in reduced complexity for updating parameter estimates at each network node. We explore cooperation strategies in adaptive distributed sensor networks for reduction in information exchange between cooperating nodes, and search for an optimal strategy to obtain consensus estimates.

S³ seminar : Big Data in the Social Sciences: Statistical methods for multi-source high-dimensional data

Seminar on October 06, 2017, 10:00 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Katrijn Van Deun (Tilburg University, the Netherlands)


Research in the behavioural and social sciences has entered the era of big data: Many detailed measurements are taken and multiple sources of information are used to unravel complex multivariate relations. For example, in studying obesity as the outcome of environmental and genetic influences, researchers increasingly collect survey, dietary, biomarker and genetic data from the same individuals.

Although linked more-variables-than-samples (called high-dimensional) multi-source data form an extremely rich resource for research, extracting meaningful and integrated information is challenging and not appropriately addressed by current statistical methods. A first problem is that relevant information is hidden in a bulk of irrelevant variables with a high risk of finding incidental associations. Second, the sources are often very heterogeneous, which may obscure apparent links between the shared mechanisms.

In this presentation we will discuss the challenges associated to the analysis of large scale multi-source data and present state-of-the-art statistical approaches to address the challenges.

S³ seminar : Recursive State Estimation for Nonlinear Stochastic Systems and Application to a Continuous Glucose Monitoring System

Seminar on June 09, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Alexandros Charalampidis (CentraleSupélec, Rennes)


The talk will start with an introduction to recursive state estimation. It will be presented how the problem can be solved exactly in two important cases (systems with finite state space and linear Gaussian systems). The difficulties associated with nonlinear systems will be explained and the main techniques will be presented (Extended Kalman Filter, Unscented Kalman Filter, Gauss-Hermite Kalman Filter, Particle Filtering, Gaussian Sums). Then the talk will focus on systems that consist of linear dynamical systems interconnected through static nonlinear characteristics. It will be explained that for them, it is possible to avoid integration on the space space, which may be of high order, reducing it to the solution of some linear systems and low-order integration. This way, more accurate calculations can be made. Additionally, a novel quadrature technique, alternative to the Gauss-Hermite quadrature, specially designed for nonlinear filters using norm minimization concepts will be presented. The proposed techniques are applied to an example and it is shown that they can lead to a significant improvement. The final part of the talk will deal with the application of filters to data from a Continuous Glucose Monitoring System (CGMS). The importance of the CGMS to the construction of an artificial pancreas will be explained. It will be shown that, using simple models of the system dynamics, the application of Kalman and Particle Filtering to experimental data from ICU patients leads to an important reduction of the glucose estimation error.

S³ seminar : Inversion de données en traitement du signal et des images : régularisation parcimonieuse et algorithmes de minimisation L0.

Seminar on May 23, 2017, 2:00 PM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Charles SOUSSEN, (Centre de Recherche en Automatique de Nancy (CRAN, UMR CNRS 7039), Université de Lorraine)


Dans la première partie de l'exposé, je présenterai différents problèmes inverses auxquels je me suis intéressé ces dernières années et les contextes applicatifs associés : reconstruction d'images en tomographie, analyse d'images biologiques et d'images hyperspectrales en microscopie, problèmes d'inversion de données en spectroscopie optique avec applications biomédicales. Lorsque les données disponibles sont en nombre limité et partiellement informatives sur la quantité à estimer (problèmes inverses mal posés), la prise en compte d’informations a priori sur les inconnues est indispensable, et s’effectue par le biais des techniques de régularisation. Dans la seconde partie de l'exposé, je présenterai plus particulièrement la régularisation parcimonieuse de problèmes inverses, basée sur la minimisation de la "norme" l0. Les algorithmes heuristiques proposés sont conçus pour minimiser des critères mixtes L2-L0 du type

min_x J(x;lambda) = || y - Ax ||_2^2 + lambda || x ||_0.

Ce problème d'optimisation est connu pour être fortement non-convexe et NP-difficile. Les heuristiques proposées (appelées algorithmes "gloutons") sont définies en tant qu'extensions d'Orthogonal Least Squares (OLS). Leur développement est motivé par le très bon comportement empirique d'OLS et de ses versions dérivées lorsque la matrice A est mal conditionnée. Je présenterai deux types d'algorithmes pour minimiser J(x;lambda) à lambda fixé et pour un continuum de valeurs de lambda. Finalement, je présenterai quelques résultats théoriques visant à garantir que les algorithmes gloutons permettent de reconstruire exactement le support d'une représentation parcimonieuse y = Ax*, c'est-à-dire le support du vecteur x*.

Biographie : Charles Soussen est né en France en 1972. Il est diplômé de l'Ecole Nationale Supérieure en Informatique et Mathématiques Appliquées, Grenoble (ENSIMAG) en 1996. Il a obtenu sa thèse en traitement du signal et des images au Laboratoire des Signaux et Systèmes (L2S), Université de Paris-Sud, Orsay, en 2000, et son Habilitation à Diriger des Recherches à l'Université de Lorraine en 2013. Il est actuellement Maître de Conférences à l'Université de Lorraine, et au Centre de Recherche en Automatique de Nancy depuis 2005. Ses thématiques de recherche concernent les problèmes inverses et l'approximation parcimonieuse.

S³ seminar : Deux trous noirs dans une meule de foin : analyse de données pour l'astronomie gravitationnelle

Seminar on May 19, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle des séminaires du L2S
Eric Chassande-Mottin, (CNRS, AstroParticule et Cosmologie, Université Paris Diderot)


Le 14 septembre 2015, les deux détecteurs du Laser Interferometer Gravitational-wave Observatory (LIGO) inauguraient une nouvelle ère pour l'astrophysique en observant pour la première fois une onde gravitationnelle issue de la fusion de deux trous noirs faisant chacun trente fois la masse du soleil environ et situés à une distance supérieure à un milliard d'années-lumière. On donnera une vue d'ensemble de cette découverte majeure en insistant sur les méthodes d'analyse de données utilisées pour sortir le signal du bruit complexe rencontré dans ces expériences.

S³ seminar : Extending Stationarity to Graph Signal Processing: a Model for Stochastic Graph Signals

Seminar on March 31, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Benjamin Girault, (University of Southern California)


During the past few years, graph signal processing has been extending the field of signal processing on Euclidean spaces to irregular spaces represented by graphs. We have seen successes ranging from the Fourier transform, to wavelets, vertex-frequency (time-frequency) decomposition, sampling theory, uncertainty principle, or convolutive filtering. One missing ingredient though are the tools to study stochastic graph signals for which the randomness introduces its own difficulties. Classical signal processing has introduced a very simple yet very rich class of stochastic signals that is at the core of the study of stochastic signals: the stationary signals. These are the signals statistically invariant through a shift of the origin of time. In this talk, we study two extensions of stationarity to graph signals, one that stems from a new translation operator for graph signals, and another one with a more sensible interpretation on the graph. In the course, we show that attempts of alternate definitions of stationarity on graphs in the recent literature are actually equivalent to our first definition. Finally, we look at a real weather dataset and show empirical evidence of stationarity.

Bio: Benjamin Girault received his License (B.Sc.) and his Master (M.Sc.) in France from École Normale Supérieure de Cachan, France, in 2009 and 2012 respectively in the field of theoretical computer science. He then received his PhD in computer science from École Normale Supérieure de Lyon, France, in December 2015. His dissertation entitled "Signal Processing on Graphs - Contributions to an Emerging Field" focused on extending the classical definition of stationary temporal signals to stationary graph signal. Currently, he is a postdoctoral scholar with Antonio Ortega and Shri Narayanan at the University of Southern California continuing his work on graph signal processing with a focus on applying these tools to understanding human behavior.

S³ seminar : Novel Algorithms for Automated Diagnosis of Neurological and Psychiatric Disorders

Seminar on March 28, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Hojjat ADELI, (The Ohio State University, Columbus, USA)


Novel algorithms are presented for data mining of time-series data and automated electroencephalogram (EEG)-based diagnosis of neurological and psychiatric disorders based on adroit integration of three different computing technologies and problem solving paradigms: neural networks, wavelets, and the chaos theory. Examples of the research performed by the author and his associates for automated diagnosis of epilepsy, the Alzheimer’s Disease, Attention Deficit Hyperactivity Disorder (ADHD), autism spectrum disorder (ASD), and Parkinson’s disease (PD) are reviewed.

Biography: Hojjat Adeli received his Ph.D. from Stanford University in 1976 at the age of 26. He is Professor of Civil, Environmental, and Geodetic Engineering, and by courtesy Professor of Biomedical Informatics, Biomedical Engineering, Neuroscience, and Neurology at The Ohio State University. He has authored over 550 publications including 15 books. He is the Founder and Editor-in-Chief of international research journals Computer-Aided Civil and Infrastructure, now in 32nd year of publication, and Integrated Computer-Aided Engineering, now in 25th year of publication, and the Editor-in-Chief of International Journal of Neural Systems. In 1998 he received the Distinguished Scholar Award from OSU, “in recognition of extraordinary accomplishment in research and scholarship”. In 2005, he was elected Distinguished Member, ASCE: "for wide-ranging, exceptional, and pioneering contributions to computing in civil engineering and extraordinary leadership in advancing the use of computing and information technologies in many engineering disciplines throughout the world.” In 2010 he was profiled as an Engineering Legend in the ASCE journal of Leadership and Management in Engineering, and Wiley established the Hojjat Adeli Award for Innovation in Computing. In 2011 World Scientific established the Hojjat Adeli Award for Outstanding Contributions in Neural Systems. He is a Fellow of IEEE, the American Association for the Advancement of Science, American Neurological Society, and American Institute for Medical and Biomedical Engineering. Among his numerous awards and honors are a special medal from Polish Neural Network Society, the Eduardo Renato Caianiello Award for Excellence in Scientific Research from the Italian Society of Neural Networks, the Omar Khayyam Research Excellence Award from Scientia Iranica, an Honorary Doctorate from Vilnius Gediminas Technical University, and corresponding member of the Spanish Royal Engineering Society.

S³ seminar : Stochastic proximal algorithms with applications to online image recovery

Seminar on March 24, 2017, 11:00 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Jean-Christophe PESQUET, CVN, CentraleSupélec


Stochastic approximation techniques have been used in various contexts in machine learning and adaptive filtering. We investigate the asymptotic behavior of a stochastic version of the forward-backward splitting algorithm for finding a zero of the sum of a maximally monotone set-valued operator and a cocoercive operator in a Hilbert space. In our general setting, stochastic approximations of the cocoercive operator and perturbations in the evaluation of the resolvents of the set-valued operator are possible. In addition, relaxations and not necessarily vanishing proximal parameters are allowed. Weak almost sure convergence properties of the iterates are established under mild conditions on the underlying stochastic processes. Leveraging on these results, we propose a stochastic version of a popular primal-dual proximal optimization algorithm, and establish its convergence. We finally show the interest of these results in an online image restoration problem.

S³ seminar : On Electromagnetic Modeling and Imaging of Defects in Periodic Fibered Laminates

Seminar on March 10, 2017, 12:30 PM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Zicheng LIU, (Inverse problems Group, Signals and Statistics Division, L2S Laboratory)


Composite laminates are commonly utilized in industry due to advantages as high stiffness, light weight, versatility, etc. Multiple layers, each one involving periodically-positioned circular-cylindrical fibers in a given homogeneous matrix, are usually involved. However, defects can affect the structure and thereupon impact security and efficiency, and they call for nondestructive testing. By electromagnetic (EM) means, it requires fast and reliable computational modeling of both sound and damaged laminates if one wishes to better understand pluses and minuses of the testing, and derive efficient imaging algorithms for the end user. Both direct modeling and inverse imaging will be introduced in this presentation.  For the former, since the periodicity of the structure is destroyed due to defects, methods based on the Floquet theorem are inapplicable. Two modeling approaches are then utilized: one is with supercell methodology where a fictitious periodic structure is fabricated, so as the EM field solution everywhere in space can be well approximately modeled, provided the supercell be large enough; the other is based on fictitious source superposition (FSS) where defects are treated as equivalent sources and the field solution is a summation of responses to the exterior source and equivalent ones. For imaging, with MUSIC and sparsity-based algorithm, missing fibers could be accurately located.

Biography: Zicheng LIU was born in Puyang, China, in October 1988. He received the M.S. degree in circuit and system from Xidian University, Xi’an, China in March 2014 and is currently pursuing the Ph.D. degree with the benefit of a Chinese Scholarship Council (CSC) grant at the Laboratoire des Signaux et Systèmes, jointly Centre National de la Recherche Scientifique (CNRS), CentraleSupélec, and Université Paris-Sud, Université Paris-Saclay, Paris, France. He will defend his Université Paris-Saclay Ph.D. early Fall 2017. His present work is on the electromagnetic modeling of damaged periodic fiber-based laminates and corresponding imaging algorithms and inversion. His research interests include computational electromagnetics, scattering theory on periodic structures, non-destructive testing, sparsity theory, and array signal processing.

S³ seminar : On Imaging Methods of Material Structures with Different Boundary Conditions

Seminar on March 10, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Xiuzhu YE, (Beihang University, Beijing, China)


This talk is about the two-dimensional inverse scattering problems for different kinds of boundary conditions. Firstly, we propose a perfect electric conductor (PEC) inverse scattering approach, which is able to reconstruct PEC objects of arbitrary number and shape without requiring prior information on the approximate locations or the number of the unknown scatterers. Secondly, the modeling scheme of the T-matrix method is introduced to solve the challenging problem of reconstructing a mixture of both PEC and dielectric scatterers together. Then the method is further extended to the case of scatterers with four boundary conditions together. Last, we propose a method to solve the dielectric and mixed boundary through-wall imaging problem. Various numerical simulations and experiments are carried out to validate the proposed methods.

Biography: Xiuzhu YE was born in Heilongjiang, China, in December 1986. She received the Bachelor degree of Communication Engineering from Harbin Institute of Technology, China, in July 2008 and the Ph.D. degree from the National University of Singapore, Singapore, in April 2012. From February 2012 to January 2013, she worked in the Department E.C.E., National University of Singapore, as a Research Fellow. Currently, she is Assistant Professor in the School of Electronic and Information Engineering of the Beihang University. She has been and is engaged under various guises with Ecole Centrale de Pékin (ECPK) also. She is presently benefiting from an invited professorship position at University Paris-Sud and later this Summer 2017 she will be benefiting from an invited professorship position at CentraleSupélec, both within the Laboratoire des Signaux et Systèmes, jointly Centre National de la Recherche Scientifique (CNRS), CentraleSupélec, and Université Paris-Sud, Université Paris-Saclay, Gif-sur-Yvette, France. Her current research interest mainly includes fast algorithms in solving inverse scattering problems, near field imaging, biomedical imaging, and antenna designing.

S³ seminar : FastText: A library for efficient learning of word representations and sentence classification

Seminar on February 24, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Piotr Bojanowski, (Facebook AI Research)


In this talk, I will describe FastText, an open-source library that can be used to train word representations or text classifiers. This library is based on our generalization of the famous word2vec model, allowing to adapt it easily to various applications. I will go over the formulation of the skipgram and cbow models of word2vec and how these were extended to meet the needs of our model. I will describe in details the two applications of our model, namely document classification and building morphologically-rich word representations. In both applications, our model achieves very competitive performance while being very simple and fast.

S³ seminar : Stochastic Quasi-Newton Langevin Monte Carlo

Seminar on February 10, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Umut Şimşekli, (LTCI, Télécom ParisTech)


Recently, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods have been proposed for scaling up Monte Carlo computations to large data problems. Whilst these approaches have proven useful in many applications, vanilla SG-MCMC might suffer from poor mixing rates when random variables exhibit strong couplings under the target densities or big scale differences. In this talk, I will present a novel SG-MCMC method that takes the local geometry into account by using ideas from Quasi-Newton optimization methods. These second order methods directly approximate the inverse Hessian by using a limited history of samples and their gradients. Our method uses dense approximations of the inverse Hessian while keeping the time and memory complexities linear with the dimension of the problem. I will provide formal theoretical analysis where it is shown that the proposed method is asymptotically unbiased and consistent with the posterior expectations. I will finally illustrate the effectiveness of the approach on both synthetic and real datasets. This is a joint work with Roland Badeau, Taylan Cemgil and Gaël Richard. arXiv: https://arxiv.org/abs/1602.03442

S³-PASADENA seminar : Detecting confounding in multivariate linear models via spectral analysis

Seminar on January 31, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Dominik Janzing, Max Planck Institute for Intelligent Systems, Tuebingen, Germany


We study a model where one target variable Y is correlated
with  a vector X:=(X_1,...,X_d) of predictor variables  being potential causes of Y.
We describe  a method that infers to what extent the statistical dependences between X and Y
are due to the influence of X on Y and to what extent due to a hidden common cause
(confounder) of X and Y. The method is based on an independence assumption stating that, in the absence of confounding,
the vector of regression coefficients describing the influence of each X on Y has 'generic orientation'
relative to the eigenspaces  of the covariance matrix of X. For the special case of a scalar confounder we show that confounding typically spoils this generic orientation in a characteristic way that can be used to quantitatively estimate the amount of confounding.
I also show some encouraging experiments with real data, but the method is work in progress and critical comments are highly appreciated.

Postulating 'generic orientation' is inspired by a more general postulate stating that
P(cause) and P(effect|cause) are independent objects of Nature and therefore don't contain information about each other [1,2,3],
an idea that inspired several causal inference methods already, e.g. [4,5].

[1] Janzing, Schoelkopf: Causal inference using the algorithmic Markov condition, IEEE TIT 2010.
[2] Lemeire, Janzing: Replacing causal faithfulness with the algorithmic independence of conditionals, Minds and Machines, 2012.
[3] Schoelkopf et al: On causal and anticausal learning, ICML 2012.
[4] Janzing et al: Telling cause frome effect based on high-dimensional observations, ICML 2010.
[5] Shajarisales et al: Telling cause from effect in deterministic linear dynamical systems, ICML 2015.

S³ Seminar: Adapting to unknown noise level in super-resolution

Seminar on January 20, 2017, 10:30 AM at CentraleSupelec (Gif-sur-Yvette) Salle du conseil du L2S - B4.40
Claire Boyer (LSTA, UPMC)


We study sparse spikes deconvolution over the space of complex-valued measures when the input measure is a finite sum of Dirac masses. We introduce a new procedure to handle the spike deconvolution when the noise level is unknown. Prediction and localization results will be presented for this approach. An insight on the probabilistic tools used in the proofs could be briefly given as well.

Pages