JMJérôme Malick

Jérôme Malick

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jérôme Malick has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Knapsack with compactness: a semidefinite approach

    by Hubert Villuendas, Mathieu Besançon, Jérôme Malick

    The min-knapsack problem with compactness constraints extends the classical knapsack problem, in the case of ordered items, by introducing a restriction ensuring that they cannot be too far apart. This problem has applications in statistics, particularly in the detection of change-points in time series. In this paper, we propose a semidefinite programming approach for this problem, incorporating compactness in constraints or in objective. We study and compare the different relaxations, and argue that our method provides high-quality heuristics and tight bounds. In particular, the single hyperparameter of our penalized semidefinite models naturally balances the trade-off between compactness and accuracy of the computed solutions. Numerical experiments illustrate, on the hardest instances, the effectiveness and versatility of our approach compared to the existing mixed-integer programming formulation.

  • The Rate of Convergence of Bregman Proximal Methods: Local Geometry Versus Regularity Versus Sharpness

    by Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos

    We examine the last-iterate convergence rate of Bregman proximal methods—from mirror descent to mirror-prox and its optimistic variants—as a function of the local geometry induced by the prox-mapping defining the method. For generality, we focus on local solutions of constrained, nonmonotone variational inequalities, and we show that the convergence rate of a given method depends sharply on its associated Legendre exponent, a notion that measures the growth rate of the underlying Bregman function (Euclidean, entropic, or other) near a solution. In particular, we show that boundary solutions exhibit a stark separation of regimes between methods with a zero and nonzero Legendre exponent: The former converge at a linear rate, while the latter converge, in general, sublinearly. This dichotomy becomes even more pronounced in linearly constrained problems where methods with entropic regularization achieve a linear convergence rate along sharp directions, compared to convergence in a finite number of steps under Euclidean regularization.


  • Harnessing Structure in Composite Nonsmooth Minimization

    by Gilles Bareilles, Franck Iutzeler, Jérôme Malick

    We consider the problem of minimizing the composition of a nonsmooth function with a smooth mapping in the case where the proximity operator of the nonsmooth function can be explicitly computed. We first show that this proximity operator can provide the exact smooth substructure of minimizers, not only of the nonsmooth function, but also of the full composite function. We then exploit this proximal identification by proposing an algorithm which combines proximal steps with sequential quadratic programming steps. We show that our method locally identifies the optimal smooth substructure and then converges quadratically. We illustrate its behavior on two problems: the minimization of a maximum of quadratic functions and the minimization of the maximal eigenvalue of a parametrized matrix.


  • Open Access

    The rate of convergence of Bregman proximal methods: Local geometry vs. regularity vs. sharpness

    by Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos

    We examine the last-iterate convergence rate of Bregman proximal methods - from mirror descent to mirror-prox and its optimistic variants - as a function of the local geometry induced by the prox-mapping defining the method. For generality, we focus on local solutions of constrained, non-monotone variational inequalities, and we show that the convergence rate of a given method depends sharply on its associated Legendre exponent, a notion that measures the growth rate of the underlying Bregman function (Euclidean, entropic, or other) near a solution. In particular, we show that boundary solutions exhibit a stark separation of regimes between methods with a zero and non-zero Legendre exponent: the former converge at a linear rate, while the latter converge, in general, sublinearly. This dichotomy becomes even more pronounced in linearly constrained problems where methods with entropic regularization achieve a linear convergence rate along sharp directions, compared to convergence in a finite number of steps under Euclidean regularization.

  • Federated learning with superquantile aggregation for heterogeneous data

    by Krishna Pillutla, Yassine Laguel, Jérôme Malick, Zaid Harchaoui


  • Open Access

    Regularization for Wasserstein distributionally robust optimization

    by Waïss Azizian, Franck Iutzeler, Jérôme Malick

    Optimal transport has recently proved to be a useful tool in various machine learning applications needing comparisons of probability measures. Among these, applications of distributionally robust optimization naturally involve Wasserstein distances in their models of uncertainty, capturing data shifts or worst-case scenarios. Inspired by the success of the regularization of Wasserstein distances in optimal transport, we study in this paper the regularization of Wasserstein distributionally robust optimization. First, we derive a general strong duality result of regularized Wasserstein distributionally robust problems. Second, we refine this duality result in the case of entropic regularization and provide an approximation result when the regularization parameters vanish.


  • Open Access

    Harnessing structure in composite nonsmooth minimization

    by Gilles Bareilles, Franck Iutzeler, Jérôme Malick

    We consider the problem of minimizing the composition of a nonsmooth function with a smooth mapping in the case where the proximity operator of the nonsmooth function can be explicitly computed. We first show that this proximity operator can provide the exact smooth substructure of minimizers, not only of the nonsmooth function, but also of the full composite function. We then exploit this proximal identification by proposing an algorithm which combines proximal steps with sequential quadratic programming steps. We show that our method locally identifies the optimal smooth substructure and then converges quadratically. We illustrate its behavior on two problems: the minimization of a maximum of quadratic functions and the minimization of the maximal eigenvalue of a parametrized matrix.


  • Open Access

    Push--Pull with Device Sampling

    by Yu-Guan Hsieh, Yassine Laguel, Franck Iutzeler, Jérôme Malick

    We consider decentralized optimization problems in which a number of agents collaborate to minimize the average of their local functions by exchanging over an underlying communication graph. Specifically, we place ourselves in an asynchronous model where only a random portion of nodes perform computation at each iteration, while the information exchange can be conducted between all the nodes and in an asymmetric fashion. For this setting, we propose an algorithm that combines gradient tracking with a network-level variance reduction (in contrast to variance reduction within each node). This enables each node to track the average of the gradients of the objective functions. Our theoretical analysis shows that the algorithm converges linearly, when the local objective functions are strongly convex, under mild connectivity conditions on the expected mixing matrices. In particular, our result does not require the mixing matrices to be doubly stochastic. In the experiments, we investigate a broadcast mechanism that transmits information from computing nodes to their neighbors, and confirm the linear convergence of our method on both synthetic and real-world datasets.

  • Push–Pull With Device Sampling

    by Yu-Guan Hsieh, Yassine Laguel, Franck Iutzeler, Jérôme Malick

    We consider decentralized optimization problems in which a number of agents collaborate to minimize the average of their local functions by exchanging over an underlying communication graph. Specifically, we place ourselves in an asynchronous model where only a random portion of nodes perform computation at each iteration, while the information exchange can be conducted between all the nodes and in an asymmetric fashion. For this setting, we propose an algorithm that combines gradient tracking with a network-level variance reduction (in contrast to variance reduction within each node). This enables the nodes to track the average of the gradients of the objective functions. Our theoretical analysis shows that the algorithm converges linearly, when the local objective functions are strongly convex, under mild connectivity conditions on the expected mixing matrices. In particular, our result does not require the mixing matrices to be doubly stochastic. In the experiments, we investigate a broadcast mechanism that transmits information from computing nodes to their neighbors, and confirm the linear convergence of our method on both synthetic and real-world datasets.