Jean-Christophe Pesquet

Convergence Results for Primal-Dual Algorithms in the Presence of Adjoint Mismatch

  • Andres Contreras
  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
  • Marion Savanier
    • Categories Convex Optimization, Nonsmooth Optimization Tags , , , , , , ,

    Most optimization problems arising in imaging science involve high-dimensional linear operators and their adjoints. In the implementations of these operators, approximations may be introduced for various practical considerations (e.g., memory limitation, computational cost, convergence speed), leading to an adjoint mismatch. This occurs for the X-ray tomographic inverse problems found in Computed Tomography (CT), where the … Read more

    Unmatched Preconditioning of the Proximal Gradient Algorithm

  • Marion Savanier
  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
  • Cyril Riddel
    • Categories Convex Optimization, Nonsmooth Optimization Tags , , , ,

    This works addresses the resolution of penalized least-squares problems using the proximal gradient algorithm (PGA). It is known that PGA can be accelerated by preconditioning strategies. However, typical effective choices of preconditioners may correspond to intricate matrices that are not easily inverted, and lead to an increased complexity in the computation of the proximity step. … Read more

    A Local MM Subspace Method for Solving Constrained Variational Problems in Image Recovery

  • Émilie Chouzenoux
  • Ségolène Martin
  • Jean-Christophe Pesquet
    • Categories Constrained Nonlinear Optimization, Convex Optimization, Nonsmooth Optimization Tags , , , , , ,

    This article introduces a new Penalized Majorization-Minimization Subspace algorithm (P-MMS) for solving smooth, constrained optimization problems. In short, our approach consists of embedding a subspace algorithm in an inexact exterior penalty procedure. The subspace strategy, combined with a Majoration-Minimization step-size search, takes great advantage of the smoothness of the penalized cost function, while the penalty … Read more

    Convergence of Proximal Gradient Algorithm in the Presence of Adjoint Mismatch

  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
  • Cyril Riddel
  • Marion Savanier
  • Yves Trousset
    • Categories Convex Optimization, Nonsmooth Optimization Tags , , , , , ,

    We consider the proximal gradient algorithm for solving penalized least-squares minimization problems arising in data science. This first-order algorithm is attractive due to its flexibility and minimal memory requirements allowing to tackle large-scale minimization problems involving non-smooth penalties. However, for problems such as X-ray computed tomography, the applicability of the algorithm is dominated by the … Read more

    A Proximal Interior Point Algorithm with Applications to Image Processing

  • Émilie Chouzenoux
  • Marie-Caroline Corbineau
  • Jean-Christophe Pesquet
    • Categories Constrained Nonlinear Optimization, Convex Optimization, Nonsmooth Optimization Tags , , , , , , , ,

    In this article, we introduce a new proximal interior point algorithm (PIPA). This algorithm is able to handle convex optimization problems involving various constraints where the objective function is the sum of a Lipschitz differentiable term and a possibly nonsmooth one. Each iteration of PIPA involves the minimization of a merit function evaluated for decaying … Read more

    General risk measures for robust machine learning

  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
  • Henri Gérard
    • Categories Convex Optimization, Robust Optimization, Stochastic Programming Tags , , , , ,

    A wide array of machine learning problems are formulated as the minimization of the expectation of a convex loss function on some parameter space. Since the probability distribution of the data of interest is usually unknown, it is is often estimated from training sets, which may lead to poor out-of-sample performance. In this work, we … Read more

    Deep Unfolding of a Proximal Interior Point Method for Image Restoration

  • Carla Bertocchi
  • Émilie Chouzenoux
  • Marie-Caroline Corbineau
  • Jean-Christophe Pesquet
  • Marco Prato
    • Categories Convex and Nonsmooth Optimization, Network Optimization, Robust Optimization Tags , , , , ,

    Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters, which can be estimated through computationally expensive and time-consuming methods. In contrast, deep learning offers very generic and efficient … Read more

    Deep Neural Network Structures Solving Variational Inequalities

  • Patrick L. Combettes
  • Jean-Christophe Pesquet
    • Categories Complementarity and Variational Inequalities, Convex Optimization Tags , , , ,

    We propose a novel theoretical framework to investigate deep neural networks using the formalism of proximal fixed point methods for solving variational inequalities. We first show that almost all activation functions used in neural networks are actually proximity operators. This leads to an algorithmic model alternating firmly nonexpansive and linear operators. We derive new results … Read more

    Proximal Approaches for Matrix Optimization Problems: Application to Robust Precision Matrix Estimation.

  • A. Benfenati
  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
    • Categories Applications - OR and Management Sciences Tags , , , , ,

    In recent years, there has been a growing interest in mathematical mod- els leading to the minimization, in a symmetric matrix space, of a Bregman di- vergence coupled with a regularization term. We address problems of this type within a general framework where the regularization term is split in two parts, one being a spectral … Read more

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

  • Luis M. Briceno-Arias
  • Émilie Chouzenoux
  • Jean-Christophe Pesquet
  • Giovanni Chierchia
    • Categories Convex Optimization, Statistics Tags , , ,

    In this paper, we propose a new optimization algorithm for sparse logistic regression based on a stochastic version of the Douglas Rachford splitting method. Our 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 … Read more