Imagen de Portada

Wasserstein proximal operators describe score-based generative models and resolve memorization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Benjamin J., Liu, Siting, Li, Wuchen, Katsoulakis, Markos A., Osher, Stanley J.
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
por: Zhang, Benjamin J., et al.
Publicado: (2025)

Equivariant score-based generative models provably learn distributions with symmetries efficiently
por: Chen, Ziyu, et al.
Publicado: (2024)

Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows
por: Gu, Hyemin, et al.
Publicado: (2024)

Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with $L_1$ Prior
por: Han, Fuqun, et al.
Publicado: (2025)

Tensor train based sampling algorithms for approximating regularized Wasserstein proximal operators
por: Han, Fuqun, et al.
Publicado: (2024)

Score-based generative models are provably robust: an uncertainty quantification perspective
por: Mimikos-Stamatopoulos, Nikiforos, et al.
Publicado: (2024)

Preconditioned Regularized Wasserstein Proximal Sampling
por: Tan, Hong Ye, et al.
Publicado: (2025)

Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
por: Kan, Kelvin, et al.
Publicado: (2026)

Accelerated Regularized Wasserstein Proximal Sampling Algorithms
por: Tan, Hong Ye, et al.
Publicado: (2026)

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
por: Kan, Kelvin, et al.
Publicado: (2025)

A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations
por: Liu, Shu, et al.
Publicado: (2024)

Stability of Transformers under Layer Normalization
por: Kan, Kelvin, et al.
Publicado: (2025)

Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems
por: Zhou, Mo, et al.
Publicado: (2024)

Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
por: Yang, Liu, et al.
Publicado: (2023)

Nonlinear denoising score matching for enhanced learning of structured distributions
por: Birrell, Jeremiah, et al.
Publicado: (2024)

Simulating Fokker-Planck equations via mean field control of score-based normalizing flows
por: Zhou, Mo, et al.
Publicado: (2025)

A Primal-dual hybrid gradient method for solving optimal control problems and the corresponding Hamilton-Jacobi PDEs
por: Meng, Tingwei, et al.
Publicado: (2024)

Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals
por: Han, Fuqun, et al.
Publicado: (2024)

Splitting Regularized Wasserstein Proximal Algorithms for Nonsmooth Sampling Problems
por: Han, Fuqun, et al.
Publicado: (2025)

A deep learning algorithm for computing mean field control problems via forward-backward score dynamics
por: Zhou, Mo, et al.
Publicado: (2024)

Proximal optimal transport divergences
por: Baptista, Ricardo, et al.
Publicado: (2025)

PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws
por: Yang, Liu, et al.
Publicado: (2024)

Neural Implicit Solution Formula for Efficiently Solving Hamilton-Jacobi Equations
por: Park, Yesom, et al.
Publicado: (2025)

Sample Complexity of Probability Divergences under Group Symmetry
por: Chen, Ziyu, et al.
Publicado: (2023)

Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
por: Cheng, Xiuyuan, et al.
Publicado: (2023)

Robust Generative Learning with Lipschitz-Regularized $α$-Divergences Allows Minimal Assumptions on Target Distributions
por: Chen, Ziyu, et al.
Publicado: (2024)

Causality and Bayesian network PDEs for multiscale representations of porous media
por: Um, Kimoon, et al.
Publicado: (2019)

ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
por: Zhang, Zhizhen, et al.
Publicado: (2026)

Numerical Analysis on Neural Network Projected Schemes for Approximating One Dimensional Wasserstein Gradient Flows
por: Zuo, Xinzhe, et al.
Publicado: (2024)

Losing dimensions: Geometric memorization in generative diffusion
por: Achilli, Beatrice, et al.
Publicado: (2024)

OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization
por: Kan, Kelvin, et al.
Publicado: (2025)

Statistical Guarantees of Group-Invariant GANs
por: Chen, Ziyu, et al.
Publicado: (2023)

Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data
por: Gu, Hyemin, et al.
Publicado: (2022)

Gradient-adjusted underdamped Langevin dynamics for sampling
por: Zuo, Xinzhe, et al.
Publicado: (2024)

Scalability of memorization-based machine unlearning
por: Zhao, Kairan, et al.
Publicado: (2024)

Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
por: Park, Yesom, et al.
Publicado: (2025)

A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptions
por: Negrini, Elisa, et al.
Publicado: (2025)

Measuring memorization in language models via probabilistic extraction
por: Hayes, Jamie, et al.
Publicado: (2024)

Exploring prompts to elicit memorization in masked language model-based named entity recognition
por: Xia, Yuxi, et al.
Publicado: (2024)

An analysis of the noise schedule for score-based generative models
por: Strasman, Stanislas, et al.
Publicado: (2024)