What is he best known for?
The fields of study he is best known for:
- Statistics
- Artificial intelligence
- Algorithm
Jean-Christophe Pesquet spends much of his time researching Mathematical optimization, Convex optimization, Algorithm, Wavelet and Optimization problem.
His research in Mathematical optimization intersects with topics in Deconvolution, Convergence, Hilbert space, Convex analysis and Image restoration.
His Convex optimization study combines topics from a wide range of disciplines, such as Iterative method, Convex function and Monotone polygon.
His work deals with themes such as Orthonormal basis and Multiresolution analysis, which intersect with Algorithm.
Within one scientific family, Jean-Christophe Pesquet focuses on topics pertaining to Differentiable function under Optimization problem, and may sometimes address concerns connected to Inverse problem, Critical point, Subspace topology and Sparse image.
His research integrates issues of Conic optimization, Linear subspace and Proper convex function in his study of Proximal Gradient Methods.
His most cited work include:
- Proximal Splitting Methods in Signal Processing (1537 citations)
- A Douglas–Rachford Splitting Approach to Nonsmooth Convex Variational Signal Recovery (442 citations)
- Time-invariant orthonormal wavelet representations (364 citations)
What are the main themes of his work throughout his whole career to date?
Jean-Christophe Pesquet spends much of his time researching Algorithm, Mathematical optimization, Artificial intelligence, Convex optimization and Wavelet.
He has included themes like Image restoration and Iterative reconstruction in his Algorithm study.
His Mathematical optimization research is multidisciplinary, incorporating elements of Image processing, Convergence, Inverse problem and Convex analysis.
He interconnects Computer vision and Pattern recognition in the investigation of issues within Artificial intelligence.
His Convex optimization research is multidisciplinary, incorporating perspectives in Monotone polygon, Minification, Iterative method, Convex function and Parallel algorithm.
His research investigates the connection with Monotone polygon and areas like Hilbert space which intersect with concerns in Applied mathematics.
He most often published in these fields:
- Algorithm (39.88%)
- Mathematical optimization (33.53%)
- Artificial intelligence (28.70%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial neural network (6.95%)
- Artificial intelligence (28.70%)
- Algorithm (39.88%)
In recent papers he was focusing on the following fields of study:
Jean-Christophe Pesquet focuses on Artificial neural network, Artificial intelligence, Algorithm, Applied mathematics and Convex optimization.
His Artificial intelligence course of study focuses on Computer vision and Imaging phantom.
His Interior point method study in the realm of Algorithm connects with subjects such as Operator.
His Applied mathematics study also includes fields such as
- Nonlinear system, which have a strong connection to Rational function, Optimization problem, Affine transformation, Monotonic function and Piecewise,
- Moment problem that intertwine with fields like Measure and Polynomial,
- Global optimization which is related to area like Gaussian noise.
His Rational function research integrates issues from Mathematical optimization, Relaxation and Signal reconstruction.
His Convex optimization study combines topics in areas such as Fixed point, Monotone polygon, Inverse problem, Image processing and Convergence.
Between 2018 and 2021, his most popular works were:
- Deep Neural Network Structures Solving Variational Inequalities (33 citations)
- Deep unfolding of a proximal interior point method for image restoration (32 citations)
- Lipschitz Certificates for Neural Network Structures Driven by Averaged Activation Operators (16 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Artificial intelligence
- Algorithm
Jean-Christophe Pesquet mainly focuses on Artificial neural network, Applied mathematics, Algorithm, Artificial intelligence and Lipschitz continuity.
In general Artificial neural network, his work in Recurrent neural network is often linked to Layer linking many areas of study.
His studies in Applied mathematics integrate themes in fields like Optimization problem, Rational function and Nonlinear system.
His Algorithm research includes elements of Optimization algorithm, Lambert W function and Training set.
He combines subjects such as Image processing and Robustness with his study of Lipschitz continuity.
His Iterated function study deals with Fixed point intersecting with Convex optimization.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
