YMYoussef Marzouk

Youssef Marzouk

*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


Youssef Marzouk has a total of 135 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Preserving linear invariants in ensemble filtering methods

    by Mathieu Le Provost, Jan Glaubitz, Youssef Marzouk

  • Open Access

    Learning Paths for Dynamic Measure Transport: A Control Perspective

    by Aimee Maurais, Bamdad Hosseini, Youssef Marzouk

    We bring a control perspective to the problem of identifying paths of measures for sampling via dynamic measure transport (DMT). We highlight the fact that commonly used paths may be poor choices for DMT and connect existing methods for learning alternate paths to mean-field games. Based on these connections we pose a flexible family of optimization problems for identifying tilted paths of measures for DMT and advocate for the use of objective terms which encourage smoothness of the corresponding velocities. We present a numerical algorithm for solving these problems based on recent Gaussian process methods for solution of partial differential equations and demonstrate the ability of our method to recover more efficient and smooth transport models compared to those which use an untilted reference path.

  • Open Access

    Precise asymptotic analysis of Sobolev training for random feature models

    by Katharine E Fisher, Matthew Tc Li, Youssef Marzouk, Timo Schorlepp

    Gradient information is widely useful and available in applications, and is therefore natural to include in the training of neural networks. Yet little is known theoretically about the impact of Sobolev training -- regression with both function and gradient data -- on the generalization error of highly overparameterized predictive models in high dimensions. In this paper, we obtain a precise characterization of this training modality for random feature (RF) models in the limit where the number of trainable parameters, input dimensions, and training data tend proportionally to infinity. Our model for Sobolev training reflects practical implementations by sketching gradient data onto finite dimensional subspaces. By combining the replica method from statistical physics with linearizations in operator-valued free probability theory, we derive a closed-form description for the generalization errors of the trained RF models. For target functions described by single-index models, we demonstrate that supplementing function data with additional gradient data does not universally improve predictive performance. Rather, the degree of overparameterization should inform the choice of training method. More broadly, our results identify settings where models perform optimally by interpolating noisy function and gradient data.

  • Open Access

    Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD

    by Andrey Bryutkin, Youssef Marzouk

    Lattice field theories are fundamental testbeds for computational physics; yet, sampling their Boltzmann distributions remains challenging due to multimodality and long-range correlations. While normalizing flows offer a promising alternative, their application to large lattices is often constrained by prohibitive memory requirements and the challenge of maintaining sufficient model expressivity. We propose sparse triangular transport maps that explicitly exploit the conditional independence structure of the lattice graph under periodic boundary conditions using monotone rectified neural networks (MRNN). We introduce a comprehensive framework for triangular transport maps that navigates the fundamental trade-off between \emph{exact sparsity} (respecting marginal conditional independence in the target distribution) and \emph{approximate sparsity} (computational tractability without fill-ins). Restricting each triangular map component to a local past enables site-wise parallel evaluation and linear time complexity in lattice size $N$, while preserving the expressive, invertible structure. Using $φ^4$ in two dimensions as a controlled setting, we analyze how node labelings (orderings) affect the sparsity and performance of triangular maps. We compare against Hybrid Monte Carlo (HMC) and established flow approaches (RealNVP).

  • Open Access

    Uncertainty Quantification of Fluid Leakage and Fault Instability in Geologic CO2 ${\text{CO}}_{2}$ Storage

    by Hannah Lu, Lluís Saló‐Salgado, Youssef M. Marzouk, Ruben Juanes

    Geologic storage is an important strategy for reducing greenhouse gas emissions to the atmosphere and mitigating climate change. In this process, coupling between mechanical deformation and fluid flow in fault zones is a key determinant of fault instability, induced seismicity, and leakage. Using a recently developed methodology, PREDICT, we obtain probability distributions of the permeability tensor in faults from the stochastic placement of clay smears that accounts for geologic uncertainty. We build a comprehensive set of fault permeability scenarios from PREDICT and investigate the effects of uncertainties from the fault zone internal structure and composition on forecasts of permanence and fault stability. To tackle the prohibitively expensive computational cost of the large number of simulations required to quantify uncertainty, we develop a deep‐learning‐based surrogate model capable of predicting flow migration, pressure buildup, and geomechanical responses in storage operations. We also compare our probabilistic estimation of leakage and fault instability with previous studies based on deterministic estimates of fault permeability. The results highlight the importance of including uncertainty and anisotropy in modeling of complex fault structures and improved management of geologic storage projects.


  • Open Access

    Data Assimilation: From Mathematical and Statistical Foundations to Applications

    by Jana de Wiljes, Youssef Marzouk, Aretha Teckentrup

    Data assimilation, where predictions from a dynamical system are updated sequentially based on new and incomplete observations, is increasingly finding applications in many areas of science and technology. This workshop brought together a collection of scientists from dynamical systems, statistics, machine learning, applied probability, uncertainty quantification, and mathematical modelling, as well as practitioners in the field.

  • Open Access

    Efficient sampling for sparse Bayesian learning using hierarchical prior normalization

    by Jan Glaubitz, Youssef Marzouk

    We introduce an approach for efficient Markov chain Monte Carlo (MCMC) sampling for challenging high-dimensional distributions in sparse Bayesian learning (SBL). The core innovation involves using hierarchical prior-normalizing transport maps (TMs), which are deterministic couplings that transform the sparsity-promoting SBL prior into a standard normal one. We analytically derive these prior-normalizing TMs by leveraging the product-like form of SBL priors and Knothe--Rosenblatt (KR) rearrangements. These transform the complex target posterior into a simpler reference distribution equipped with a standard normal prior that can be sampled more efficiently. Specifically, one can leverage the standard normal prior by using more efficient, structure-exploiting samplers. Our numerical experiments on various inverse problems -- including signal deblurring, inverting the non-linear inviscid Burgers equation, and recovering an impulse image -- demonstrate significant performance improvements for standard MCMC techniques.

  • Open Access

    Priorconditioned Sparsity-Promoting Projection Methods for Deterministic and Bayesian Linear Inverse Problems

    by Jonathan Lindbloom, Mirjeta Pasha, Jan Glaubitz, Youssef Marzouk

    High-quality reconstructions of signals and images with sharp edges are needed in a wide range of applications. To overcome the large dimensionality of the parameter space and the complexity of the regularization functional, {sparisty-promoting} techniques for both deterministic and hierarchical Bayesian regularization rely on solving a sequence of high-dimensional iteratively reweighted least squares (IRLS) problems on a lower-dimensional subspace. Generalized Krylov subspace (GKS) methods are a particularly potent class of hybrid Krylov schemes that efficiently solve sequences of IRLS problems by projecting large-scale problems into a relatively small subspace and successively enlarging it. We refer to methods that promote sparsity and use GKS as S-GKS. A disadvantage of S-GKS methods is their slow convergence. In this work, we propose techniques that improve the convergence of S-GKS methods by combining them with priorconditioning, which we refer to as PS-GKS. Specifically, integrating the PS-GKS method into the IAS algorithm allows us to automatically select the shape/rate parameter of the involved generalized gamma hyper-prior, which is often fine-tuned otherwise. Furthermore, we proposed and investigated variations of the proposed PS-GKS method, including restarting and recycling (resPS-GKS and recPS-GKS). These respectively leverage restarted and recycled subspaces to overcome situations when memory limitations of storing the basis vectors are a concern. We provide a thorough theoretical analysis showing the benefits of priorconditioning for sparsity-promoting inverse problems. Numerical experiment are used to illustrate that the proposed PS-GKS method and its variants are competitive with or outperform other existing hybrid Krylov methods.

  • Open Access

    Learning Local Neighborhoods of Non-Gaussian Graphical Models

    by Sarah Liaw, Rebecca Morrison, Youssef Marzouk, Ricardo Baptista

    Identifying the Markov properties or conditional independencies of a collection of random variables is a fundamental task in statistics for modeling and inference. Existing approaches often learn the structure of a probabilistic graph, which encodes these dependencies, by assuming that the variables follow a distribution with a simple parametric form. Moreover, the computational cost of many algorithms scales poorly for high-dimensional distributions, as they need to estimate all the edges in the graph simultaneously. In this work, we propose a scalable algorithm to infer the conditional independence relationships of each variable by exploiting the local Markov property. The proposed method, named Localized Sparsity Identification for Non-Gaussian Distributions (L-SING), estimates the graph by using flexible classes of transport maps to represent the conditional distribution for each variable. We show that L-SING includes existing approaches, such as neighborhood selection with Lasso, as a special case. We demonstrate the effectiveness of our algorithm in both Gaussian and non-Gaussian settings by comparing it to existing methods. Lastly, we show the scalability of the proposed approach by applying it to high-dimensional non-Gaussian examples, including a biological dataset with more than 150 variables.