3 citations · 8 across the 16 of their papers we have counts for
16 papers
One-Shot Generative Flows: Existence and Obstructions
Panos Tsimpos, Daniel Sharp, Youssef Marzouk
We study dynamic measure transport for generative modeling, focusing on transport maps that connect a source measure to a target measure by integrating a velocity field…
Data Curation for Machine Learning Interatomic Potentials by Determinantal Point Processes
Joanna Zou, Youssef Marzouk
The development of machine learning interatomic potentials faces a critical computational bottleneck with the generation and labeling of useful training datasets. We present a nove…
Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation
Qidong Yang, Qianyu Julie Zhu, Jonathan Giezendanner +3
Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge…
Generative Modeling through Koopman Spectral Analysis: An Operator-Theoretic Perspective
Yuanchao Xu, Fengyi Li, Masahiro Fujisawa +3
We propose Koopman Spectral Wasserstein Gradient Descent (KSWGD), a particle-based generative modeling framework that learns the Langevin generator via Koopman theory and integrate…
Learning Paths for Dynamic Measure Transport: A Control Perspective
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…
Localized Diffusion Models
Georg A. Gottwald, Shuigen Liu, Youssef Marzouk +2
Diffusion models are state-of-the-art tools for various generative tasks. Yet training these models involves estimating high-dimensional score functions, a task that in principle s…
Optimal Scheduling of Dynamic Transport
Panos Tsimpos, Zhi Ren, Jakob Zech +1
Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measur…
Distribution learning via neural differential equations: minimal energy regularization and approximation theory
Youssef Marzouk, Zhi Ren, Jakob Zech
Neural ordinary differential equations (ODEs) provide expressive representations of invertible transport maps that can be used to approximate complex probability distributions, e.g…
Weighted quantization using MMD: From mean field to mean shift via gradient flows
Ayoub Belhadji, Daniel Sharp, Youssef Marzouk
Approximating a probability distribution using a set of particles is a fundamental problem in machine learning and statistics, with applications including clustering and quantizati…
On the design of scalable, high-precision spherical-radial Fourier features
Ayoub Belhadji, Qianyu Julie Zhu, Youssef Marzouk
Approximation using Fourier features is a popular technique for scaling kernel methods to large-scale problems, with myriad applications in machine learning and statistics. This me…
Sharp detection of low-dimensional structure in probability measures via dimensional logarithmic Sobolev inequalities
Matthew T. C. Li, Tiangang Cui, Fengyi Li +2
Identifying low-dimensional structure in high-dimensional probability measures is an essential pre-processing step for efficient sampling. We introduce a method for identifying and…
Nonlinear Bayesian optimal experimental design using logarithmic Sobolev inequalities
Fengyi Li, Ayoub Belhadji, Youssef Marzouk
We study the problem of selecting experiments from a larger candidate pool, where the goal is to maximize mutual information (MI) between the selected subset and the underlying…
Stable generative modeling using Schrödinger bridges
Georg A. Gottwald, Fengyi Li, Youssef Marzouk +1
We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. Such settings have recently drawn con…
Sampling in Unit Time with Kernel Fisher-Rao Flow
Aimee Maurais, Youssef Marzouk
We introduce a new mean-field ODE and corresponding interacting particle systems (IPS) for sampling from an unnormalized target density. The IPS are gradient-free, available in clo…
Wasserstein-based Minimax Estimation of Dependence in Multivariate Regularly Varying Extremes
Xuhui Zhang, Jose Blanchet, Youssef Marzouk +2
We present the first minimax risk bounds for estimators of the spectral measure in multivariate linear factor models, where observations are linear combinations of regularly varyin…
Distribution learning via neural differential equations: a nonparametric statistical perspective
Youssef Marzouk, Zhi Ren, Sven Wang +1
Ordinary differential equations (ODEs), via their induced flow maps, provide a powerful framework to parameterize invertible transformations for the purpose of representing complex…