HKHicham Kouhkouh

Hicham Kouhkouh

*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


Hicham Kouhkouh has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Faithful Global Convergence for the Rescaled Consensus–Based Optimization

    by Hui Huang, Hicham Kouhkouh, Lukang Sun

    We analyze the consensus-based optimization algorithm with a consensus point rescaled by a fixed parameter [Formula: see text]. Under minimal assumptions on the objective function and the initial data, we establish its unconditional convergence to the global minimizer. Our results hold in the asymptotic regime where the time horizon [Formula: see text] and the inverse temperature [Formula: see text] are taken successively, providing a rigorous theoretical foundation for the algorithm’s global convergence. Furthermore, our findings extend to the case of multiple and nondiscrete set of minimizers.

  • Open Access

    Uniform-in-time mean-field limit estimate for the Consensus-Based Optimization

    by Hui Huang, Hicham Kouhkouh

    We establish a uniform-in-time estimate for the mean-field convergence of the Consensus- Based Optimization (CBO) algorithm by rescaling the consensus point in the dynamics with a small parameter κ ∈ (0, 1). This uniform-in-time estimate is essential, as CBO convergence relies on a sufficiently large time horizon and is crucial for ensuring stable, reliable long-term convergence, the latter being key to the practical effectiveness of CBO methods.


  • A multiscale consensus-based algorithm for multilevel optimization

    by Michael Herty, Yuyang Huang, Dante Kalise, Hicham Kouhkouh

    In this paper, a novel multiscale consensus-based optimization (CBO) algorithm for solving bi- and tri-level optimization problems is introduced. Existing CBO techniques are generalized by the proposed method through the employment of multiple interacting populations of particles, each of which is used to optimize one level of the problem. These particle populations are evolved through multiscale-in-time dynamics, which are formulated as a singularly perturbed system of stochastic differential equations. Theoretical convergence analysis for the multiscale CBO model to an averaged effective dynamics as the time-scale separation parameter approaches zero is provided. The resulting algorithm is presented for both bi-level and tri-level optimization problems. The effectiveness of the approach in tackling complex multilevel optimization tasks is demonstrated through numerical experiments on various benchmark functions. Additionally, it is shown that the proposed method performs well on min–max optimization problems, comparing favorably with existing CBO algorithms for saddle point problems.


  • Deep Relaxation of Controlled Stochastic Gradient Descent via Singular Perturbations

    by Martino Bardi, Hicham Kouhkouh

    We consider a singularly perturbed system of stochastic differential equations proposed by Chaudhari et al. (Res. Math. Sci. 2018) to approximate the entropic gradient descent in the optimization of deep neural networks via homogenization. We embed it in a much larger class of two-scale stochastic control problems and rely on convergence results for Hamilton–Jacobi–Bellman equations with unbounded data proved recently by ourselves (ESAIM Control Optim. Calc. Var. 2023). We show that the limit of the value functions is itself the value function of an effective control problem with extended controls and that the trajectories of the perturbed system converge in a suitable sense to the trajectories of the limiting effective control system. These rigorous results improve the understanding of the convergence of the algorithms used by Chaudhari et al., as well as of their possible extensions where some tuning parameters are modeled as dynamic controls.


  • Long-Time Behavior of Deterministic Mean Field Games with Nonmonotone Interactions

    by Martino Bardi, Hicham Kouhkouh

    We consider deterministic mean field games (MFGs) in all Euclidean space with a cost functional continuous with respect to the distribution of the agents and attaining its minima in a compact set. We first show that the static MFG with such a cost has an equilibrium, and we build from it a solution of the ergodic MFG system of first order PDEs with the same cost. Next we address the long-time limit of the solutions to finite horizon MFGs with cost functional satisfying various additional assumptions, but not the classical Lasry–Lions monotonicity condition. Instead we assume that the cost has the same set of minima for all measures describing the population. We prove the convergence of the distribution of the agents and of the value function to a solution of the ergodic MFG system as the horizon of the game tends to infinity, extending to this class of MFGs some results of weak KAM theory.


  • Open Access

    Relaxation and asymptotic expansion of controlled stiff differential equations

    by Michael Herty, Hicham Kouhkouh

    The control of relaxation-type systems of ordinary differential equations is investigated using the Hamilton-Jacobi-Bellman equation. First, we recast the model as a singularly perturbed dynamics which we embed in a family of controlled systems. Then we study this dynamics together with the value function of the associated optimal control problem. We provide an asymptotic expansion in the relaxation parameter of the value function. We also show that its solution converges toward the solution of a Hamilton-Jacobi-Bellman equation for a reduced control problem. Such systems are motivated by semi-discretisation of kinetic and hyperbolic partial differential equations. Several examples are presented including Jin-Xin relaxation.

  • Open Access

    Long-time behaviour of deterministic Mean Field Games with non-monotone interactions

    by Martino Bardi, Hicham Kouhkouh

    We consider deterministic Mean Field Games (MFG) in all Euclidean space with a cost functional continuous with respect to the distribution of the agents and attaining its minima in a compact set. We first show that the static MFG with such a cost has an equilibrium, and we build from it a solution of the ergodic MFG system of 1st order PDEs with the same cost. Next we address the long-time limit of the solutions to finite horizon MFG with cost functional satisfying various additional assumptions, but not the classical Lasry-Lions monotonicity condition. Instead we assume that the cost has the same set of minima for all measures describing the population. We prove the convergence of the distribution of the agents and of the value function to a solution of the ergodic MFG system as the horizon of the game tends to infinity, extending to this class of MFG some results of weak KAM theory.

  • Open Access

    Deep Relaxation of Controlled Stochastic Gradient Descent via Singular Perturbations

    by Martino Bardi, Hicham Kouhkouh

    We consider a singularly perturbed system of stochastic differential equations proposed by Chaudhari et al. (Res. Math. Sci. 2018) to approximate the Entropic Gradient Descent in the optimization of deep neural networks, via homogenisation. We embed it in a much larger class of two-scale stochastic control problems and rely on convergence results for Hamilton-Jacobi-Bellman equations with unbounded data proved recently by ourselves (ESAIM Control Optim. Calc. Var. 2023). We show that the limit of the value functions is itself the value function of an effective control problem with extended controls, and that the trajectories of the perturbed system converge in a suitable sense to the trajectories of the limiting effective control system. These rigorous results improve the understanding of the convergence of the algorithms used by Chaudhari et al., as well as of their possible extensions where some tuning parameters are modelled as dynamic controls.

  • A Viscous Ergodic Problem with Unbounded and Measurable Ingredients, Part 1: HJB Equation

    by Hicham Kouhkouh

    We address the problem of existence and uniqueness of solutions [Formula: see text] to ergodic Hamilton–Jacobi–Bellman (HJB) equations of the form [Formula: see text] in the whole space [Formula: see text] with unbounded and merely measurable data and where [Formula: see text] is a Bellman Hamiltonian. The method we use is different from classical approaches. It relies on duality theory and optimization in abstract Banach spaces together with maximal dissipativity of the diffusion operator.