Candès, Emmanuel J. (Emmanuel Jean)
Overview
Works:  57 works in 76 publications in 1 language and 75 library holdings 

Roles:  Author, Thesis advisor 
Publication Timeline
.
Most widely held works by
Emmanuel J Candès
Ridgelets : theory and applications by
Emmanuel J Candès(
)
4 editions published in 1998 in English and held by 5 WorldCat member libraries worldwide
Single hiddenlayer feedforward neural networks have been proposed as an approach to bypass the curse of dimensionality and are now becoming widely applied to approximation or prediction in applied sciences. In that approach, one approximates a multivariate target function by a sum of ridge functions; this is similar to projection pursuit in the literature of statistics. This approach poses new and challenging questions both at a practical and theorectical level, ranging from the construction of neural networks to their efficiency and capability. The topic of this thesis is to show that ridgelets, a new set of functions, provide an elegant tool to answer some of these fundamental questions
4 editions published in 1998 in English and held by 5 WorldCat member libraries worldwide
Single hiddenlayer feedforward neural networks have been proposed as an approach to bypass the curse of dimensionality and are now becoming widely applied to approximation or prediction in applied sciences. In that approach, one approximates a multivariate target function by a sum of ridge functions; this is similar to projection pursuit in the literature of statistics. This approach poses new and challenging questions both at a practical and theorectical level, ranging from the construction of neural networks to their efficiency and capability. The topic of this thesis is to show that ridgelets, a new set of functions, provide an elegant tool to answer some of these fundamental questions
Curvelets : a surprisingly effective nonadaptive representation for objects with edges by
Emmanuel J Candès(
Book
)
3 editions published between 1999 and 2000 in English and held by 3 WorldCat member libraries worldwide
It is widely believed that to efficiently represent an otherwise smooth object with discontinuities along edges, one must use an adaptive representation that in some sense 'tracks' the shape of the discontinuity set. This folkbelief  some would say folktheorem  is incorrect. At the very least, the possible quantitative advantage of such adaptation is vastly smaller than commonly believed. We have recently constructed a tight frame of curvelets which provides stable, efficient, and nearoptimal representation of otherwise smooth objects having discontinuities along smooth curves. By applying naive thresholding to the curvelet transform of such an object, one can form mterm approximations with rate of L(sup 2) approximation rivaling the rate obtainable by complex adaptive schemes which attempt to track' the discontinuity set. In this article we explain the basic issues of efficient mterm approximation, the construction of efficient adaptive representation, the construction of the curvelet frame, and a crude analysis of the performance of curvelet schemes
3 editions published between 1999 and 2000 in English and held by 3 WorldCat member libraries worldwide
It is widely believed that to efficiently represent an otherwise smooth object with discontinuities along edges, one must use an adaptive representation that in some sense 'tracks' the shape of the discontinuity set. This folkbelief  some would say folktheorem  is incorrect. At the very least, the possible quantitative advantage of such adaptation is vastly smaller than commonly believed. We have recently constructed a tight frame of curvelets which provides stable, efficient, and nearoptimal representation of otherwise smooth objects having discontinuities along smooth curves. By applying naive thresholding to the curvelet transform of such an object, one can form mterm approximations with rate of L(sup 2) approximation rivaling the rate obtainable by complex adaptive schemes which attempt to track' the discontinuity set. In this article we explain the basic issues of efficient mterm approximation, the construction of efficient adaptive representation, the construction of the curvelet frame, and a crude analysis of the performance of curvelet schemes
Curvelets and curvilinear integrals by
Emmanuel J Candès(
Book
)
2 editions published in 2000 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2000 in English and held by 2 WorldCat member libraries worldwide
Templates for convex cone problems with applications to sparse signal recovery by Stephen Becker(
Book
)
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
Global testing under sparse alternatives : ANOVA, multiple comparisons and the higher criticism by
Ery AriasCastro(
Book
)
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
A geometric analysis of subspace clustering with outliers by
Mahdi Soltanolkotabi(
Book
)
2 editions published in 2012 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2012 in English and held by 2 WorldCat member libraries worldwide
Harmonic analysis of neural networks by
Stanford University(
Book
)
2 editions published in 1996 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 1996 in English and held by 2 WorldCat member libraries worldwide
A Probabilistic and RIPless Theory of Compressed Sensing by
Emmanuel J Candès(
Book
)
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2010 in English and held by 2 WorldCat member libraries worldwide
Robust principal component analysis? by
Emmanuel J Candès(
Book
)
2 editions published in 2009 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2009 in English and held by 2 WorldCat member libraries worldwide
Continuous curvelet transform by
Emmanuel J Candès(
Book
)
2 editions published in 2003 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2003 in English and held by 2 WorldCat member libraries worldwide
New tight frames of curvelets and optimal representations of objects with C² singularities by
Emmanuel J Candès(
Book
)
2 editions published in 2002 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2002 in English and held by 2 WorldCat member libraries worldwide
Ridgelets : estimating with ridge functions by
Emmanuel J Candès(
Book
)
2 editions published in 1999 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 1999 in English and held by 2 WorldCat member libraries worldwide
Recovering edges in illposed inverse problems : optimality of curvelet frames by
Emmanuel J Candès(
Book
)
2 editions published in 2000 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 2000 in English and held by 2 WorldCat member libraries worldwide
On the representation of mutilated Sobolev functions by
Emmanuel J Candès(
Book
)
2 editions published in 1999 in English and held by 2 WorldCat member libraries worldwide
2 editions published in 1999 in English and held by 2 WorldCat member libraries worldwide
CONTROLLING THE FALSE DISCOVERY RATE VIA KNOCKOFFS by Rina Foygel Barber(
Book
)
1 edition published in 2014 in English and held by 1 WorldCat member library worldwide
1 edition published in 2014 in English and held by 1 WorldCat member library worldwide
Structure and Dynamics of Diffusion Networks by Manuel Gomez Rodriguez(
)
1 edition published in 2013 in English and held by 1 WorldCat member library worldwide
Diffusion of information, ideas, behaviors and diseases are ubiquitous in nature and modern society. One of the main goals of this dissertation is to shed light on the hidden underlying structure of diffusion. To this aim, we developed flexible probabilistic models and inference algorithms that make minimal assumptions about the physical, biological or cognitive mechanisms responsible for diffusion. We avoid modeling the mechanisms underlying individual activations, and instead develop a datadriven approach which uses only the visible temporal traces diffusion generates. We first developed two algorithms, NetInf and MultiTree, that infer the network structure or skeleton over which diffusion takes place. However, both algorithms assume networks to be static and diffusion to occur at equal rates across different edges. We then developed NetRate, an algorithm that allows for static and dynamic networks with different rates across different edges. NetRate infers not only the network structure but also the rate of every edge. Finally, we develop a general theoretical framework of diffusion based on survival theory. Our models and algorithms provide computational lenses for understanding the structure and temporal dynamics that govern diffusion and may help towards forecasting, influencing and retarding diffusion, broadly construed. As an application, we study information propagation in the online media space. We find that the information network of media sites and blogs tends to have a coreperiphery structure with a small set of core media sites that diffuse information to the rest of the Web. These sites tend to have stable circles of influence with more general news media sites acting as connectors between them. Information pathways for general recurrent topics are more stable across time than for ongoing news events. Clusters of news media sites and blogs often emerge and vanish in matter of days for ongoing news events. Major social movements and events involving civil population, such as the Libyan's civil war or Syria's uprise, lead to an increased amount of information pathways among blogs as well as in the overall increase in the network centrality of blogs and social media sites. Additionally, we apply our probabilistic framework of diffusion to the influence maximization problem and develop the algorithm MaxInf. Experiments on synthetic and real diffusion networks show that our algorithm outperforms other state of the art algorithms by considering the temporal dynamics of diffusion
1 edition published in 2013 in English and held by 1 WorldCat member library worldwide
Diffusion of information, ideas, behaviors and diseases are ubiquitous in nature and modern society. One of the main goals of this dissertation is to shed light on the hidden underlying structure of diffusion. To this aim, we developed flexible probabilistic models and inference algorithms that make minimal assumptions about the physical, biological or cognitive mechanisms responsible for diffusion. We avoid modeling the mechanisms underlying individual activations, and instead develop a datadriven approach which uses only the visible temporal traces diffusion generates. We first developed two algorithms, NetInf and MultiTree, that infer the network structure or skeleton over which diffusion takes place. However, both algorithms assume networks to be static and diffusion to occur at equal rates across different edges. We then developed NetRate, an algorithm that allows for static and dynamic networks with different rates across different edges. NetRate infers not only the network structure but also the rate of every edge. Finally, we develop a general theoretical framework of diffusion based on survival theory. Our models and algorithms provide computational lenses for understanding the structure and temporal dynamics that govern diffusion and may help towards forecasting, influencing and retarding diffusion, broadly construed. As an application, we study information propagation in the online media space. We find that the information network of media sites and blogs tends to have a coreperiphery structure with a small set of core media sites that diffuse information to the rest of the Web. These sites tend to have stable circles of influence with more general news media sites acting as connectors between them. Information pathways for general recurrent topics are more stable across time than for ongoing news events. Clusters of news media sites and blogs often emerge and vanish in matter of days for ongoing news events. Major social movements and events involving civil population, such as the Libyan's civil war or Syria's uprise, lead to an increased amount of information pathways among blogs as well as in the overall increase in the network centrality of blogs and social media sites. Additionally, we apply our probabilistic framework of diffusion to the influence maximization problem and develop the algorithm MaxInf. Experiments on synthetic and real diffusion networks show that our algorithm outperforms other state of the art algorithms by considering the temporal dynamics of diffusion
Oscillatory data analysis and fast algorithms for integral operators by Haizhao Yang(
)
1 edition published in 2015 in English and held by 1 WorldCat member library worldwide
This dissertation consists of two independent parts: oscillatory data analysis (Part I) and fast algorithms for integral operators in computational harmonic analysis (Part II). The first part concentrates on developing theory and efficient tools in applied and computational harmonic analysis for oscillatory data analysis. In modern data science, oscillatory data analysis aims at identifying and extracting principle wavelike components, which might be nonlinear and nonstationary, underlying a complex physical phenomenon. Estimating instantaneous properties of onedimensional components or local properties of multidimensional components has been an important topic in various science and engineering problems in resent three decades. This thesis introduces several novel synchrosqueezed transforms (SSTs) with rigorous mathematical, statistical analysis, and efficient implementation to tackle challenging problems in oscillatory data analysis. Several real applications show that these transforms provide an elegant tool for oscillatory data analysis. In many applications, the SSTbased algorithms are significantly faster than the existing stateofart algorithms and obtain better results. The second part of this thesis proposes several fast algorithms for the numerical implementation of several integral operators in harmonic analysis including Fourier integral operators (including pseudo differential operators, the generalized Radon transform, the nonuniform Fourier transform, etc.) and special function transforms (including the FourierBessel transform, the spherical harmonic transform, etc.). These are useful mathematical tools in a wide range of science and engineering problems, e.g., imaging science, weather and climate modeling, electromagnetics, quantum chemistry, and phenomena modeled by wave equations. Via hierarchical domain decomposition, randomized lowrank approximations, interpolative lowrank approximations, the fast Fourier transform, and the butterfly algorithm, I propose several novel fast algorithms for applying or recovering these operators
1 edition published in 2015 in English and held by 1 WorldCat member library worldwide
This dissertation consists of two independent parts: oscillatory data analysis (Part I) and fast algorithms for integral operators in computational harmonic analysis (Part II). The first part concentrates on developing theory and efficient tools in applied and computational harmonic analysis for oscillatory data analysis. In modern data science, oscillatory data analysis aims at identifying and extracting principle wavelike components, which might be nonlinear and nonstationary, underlying a complex physical phenomenon. Estimating instantaneous properties of onedimensional components or local properties of multidimensional components has been an important topic in various science and engineering problems in resent three decades. This thesis introduces several novel synchrosqueezed transforms (SSTs) with rigorous mathematical, statistical analysis, and efficient implementation to tackle challenging problems in oscillatory data analysis. Several real applications show that these transforms provide an elegant tool for oscillatory data analysis. In many applications, the SSTbased algorithms are significantly faster than the existing stateofart algorithms and obtain better results. The second part of this thesis proposes several fast algorithms for the numerical implementation of several integral operators in harmonic analysis including Fourier integral operators (including pseudo differential operators, the generalized Radon transform, the nonuniform Fourier transform, etc.) and special function transforms (including the FourierBessel transform, the spherical harmonic transform, etc.). These are useful mathematical tools in a wide range of science and engineering problems, e.g., imaging science, weather and climate modeling, electromagnetics, quantum chemistry, and phenomena modeled by wave equations. Via hierarchical domain decomposition, randomized lowrank approximations, interpolative lowrank approximations, the fast Fourier transform, and the butterfly algorithm, I propose several novel fast algorithms for applying or recovering these operators
ROBUST SUBSPACE CLUSTERING by
Mahdi Soltanolkotabi(
Book
)
1 edition published in 2013 in English and held by 1 WorldCat member library worldwide
1 edition published in 2013 in English and held by 1 WorldCat member library worldwide
Computational limits in statistical estimation : hidden clique and related problems by Yash Deshpande(
)
1 edition published in 2016 in English and held by 1 WorldCat member library worldwide
Characterizing computational costs of statistical estimation and inference is a fundamental challenge. In many modern applications a confluence of both largescale and highresolution data has highlighted the computational challenges in extracting information and performing inference. For a number of reasons, the hidden clique problem from theoretical computer science has emerged as a prototypical example of the impact computational considerations can have on statistical estimation problems. In particular, the computational phenomena observed in the hidden clique problem are intimately related to analogous phenomena in other problems like sparse principal components analysis and learning communities in graphs. In this thesis, we study algorithmbased computational limits for the hidden clique problem and related problems. We use the popular approaches of the belief propagation heuristic, and convex programming relaxations for two aims: 1. We propose new algorithms that provably improve over the prior stateoftheart methods for the hidden clique problem and sparse principal components analysis (PCA). 2. We provide hardness evidence for the hidden clique problem based on local algorithms, which generalize the belief propagation heuristic, and the powerful SumofSquares hierarchy of convex programming relaxations
1 edition published in 2016 in English and held by 1 WorldCat member library worldwide
Characterizing computational costs of statistical estimation and inference is a fundamental challenge. In many modern applications a confluence of both largescale and highresolution data has highlighted the computational challenges in extracting information and performing inference. For a number of reasons, the hidden clique problem from theoretical computer science has emerged as a prototypical example of the impact computational considerations can have on statistical estimation problems. In particular, the computational phenomena observed in the hidden clique problem are intimately related to analogous phenomena in other problems like sparse principal components analysis and learning communities in graphs. In this thesis, we study algorithmbased computational limits for the hidden clique problem and related problems. We use the popular approaches of the belief propagation heuristic, and convex programming relaxations for two aims: 1. We propose new algorithms that provably improve over the prior stateoftheart methods for the hidden clique problem and sparse principal components analysis (PCA). 2. We provide hardness evidence for the hidden clique problem based on local algorithms, which generalize the belief propagation heuristic, and the powerful SumofSquares hierarchy of convex programming relaxations
QuasiMonte Carlo methods in noncubical spaces by Kinjal Basu(
)
1 edition published in 2016 in English and held by 1 WorldCat member library worldwide
Monte Carlo integration is a widely used technique for approximating high dimensional integrals. However, due to the inherent randomness of this method, the convergence is typically slow. QuasiMonte Carlo (QMC) on the other hand gives a much better rate of convergence by using lowdiscrepancy sequences. These point sets are much more uniformly distributed than random samples. Most QMC research focuses on sampling from the unit cube. However, many problems in realworld applications are defined over much more general spaces, such as triangle, spheres, spherical triangles and discs. This dissertation deals with solving such problems of numerical integration defined over noncubical domains. We introduce two QMC constructions in the triangle with a vanishing discrepancy. The first is a version of the van der Corput sequence customized to the unit triangle. The second construction rotates an integer lattice through an angle whose tangent is a quadratic irrational number. We then generalize the van der Corput construction to study the problem of numerical integration over the Cartesian products of s spaces of dimension d via scrambled geometric nets. We also show the asymptotic normality of the scrambled geometric net estimator. We further discuss some of the issues of why transformations of the unit cube to the domain of interest fails to give good results. Since products of simplices is throughout of special interest to us, we end the dissertation with few results of QMC tractability on that domain
1 edition published in 2016 in English and held by 1 WorldCat member library worldwide
Monte Carlo integration is a widely used technique for approximating high dimensional integrals. However, due to the inherent randomness of this method, the convergence is typically slow. QuasiMonte Carlo (QMC) on the other hand gives a much better rate of convergence by using lowdiscrepancy sequences. These point sets are much more uniformly distributed than random samples. Most QMC research focuses on sampling from the unit cube. However, many problems in realworld applications are defined over much more general spaces, such as triangle, spheres, spherical triangles and discs. This dissertation deals with solving such problems of numerical integration defined over noncubical domains. We introduce two QMC constructions in the triangle with a vanishing discrepancy. The first is a version of the van der Corput sequence customized to the unit triangle. The second construction rotates an integer lattice through an angle whose tangent is a quadratic irrational number. We then generalize the van der Corput construction to study the problem of numerical integration over the Cartesian products of s spaces of dimension d via scrambled geometric nets. We also show the asymptotic normality of the scrambled geometric net estimator. We further discuss some of the issues of why transformations of the unit cube to the domain of interest fails to give good results. Since products of simplices is throughout of special interest to us, we end the dissertation with few results of QMC tractability on that domain
more
fewer
Audience Level
0 

1  
Kids  General  Special 
Related Identities
 Stanford University Department of Statistics
 Donoho, David Leigh
 Stanford University Department of Electrical Engineering
 Soltanolkotabi, Mahdi Author
 Plan, Yaniv Author
 Montanari, Andrea Thesis advisor
 Su, Weijie Author
 Boyd, Stephen P. Thesis advisor
 Li, Xiaodong 1985 Author
 Hastie, Trevor Thesis advisor
Useful Links
Associated Subjects
Alternative Names
Emmanuel Candès Frans wiskundige
Emmanuel Candès fransk matematikar
Emmanuel Candès fransk matematiker
Emmanuel Candès französischer Mathematiker
Emmanuel Candès French statistician
Emmanuel Candès matematico e statistico francese
Emmanuel Candès mathématicien français
Эммануэль Кандес
Languages