Image de couverture de livre

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kandasamy, Saravanan, Nagaraj, Dheeraj
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Numerical Analysis
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
par: Srinivasan, Rishikesh, et autres
Publié: (2025)

How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework
par: Ren, Yinuo, et autres
Publié: (2024)

Distillation of Discrete Diffusion through Dimensional Correlations
par: Hayakawa, Satoshi, et autres
Publié: (2024)

Constrained Ensemble Langevin Monte Carlo
par: Ding, Zhiyan, et autres
Publié: (2021)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
par: Zhan, Zhiyuan, et autres
Publié: (2026)

Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
par: Jacot, Arthur
Publié: (2026)

Provable Diffusion Posterior Sampling for Bayesian Inversion
par: Chang, Jinyuan, et autres
Publié: (2025)

Second Order Ensemble Langevin Method for Sampling and Inverse Problems
par: Liu, Ziming, et autres
Publié: (2022)

Kinetic Langevin Splitting Schemes for Constrained Sampling
par: Chada, Neil K., et autres
Publié: (2026)

ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
par: Zhu, Xianli, et autres
Publié: (2026)

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
par: Dong, Yijun, et autres
Publié: (2024)

BrowNNe: Brownian Nonlocal Neurons & Activation Functions
par: Nagaraj, Sriram, et autres
Publié: (2024)

Nonlocal Neural Tangent Kernels via Parameter-Space Interactions
par: Nagaraj, Sriram, et autres
Publié: (2025)

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
par: Modoranu, Ionut-Vlad, et autres
Publié: (2024)

Invertible ResNets for Inverse Imaging Problems: Competitive Performance with Provable Regularization Properties
par: Arndt, Clemens, et autres
Publié: (2024)

Solving Poisson Equations using Neural Walk-on-Spheres
par: Nam, Hong Chul, et autres
Publié: (2024)

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
par: Zangrando, Emanuele, et autres
Publié: (2024)

Localized Diffusion Models
par: Gottwald, Georg A., et autres
Publié: (2025)

Learning Epidemiological Dynamics via the Finite Expression Method
par: Du, Jianda, et autres
Publié: (2024)

Sampling via Stochastic Interpolants by Langevin-based Velocity and Initialization Estimation in Flow ODEs
par: Duan, Chenguang, et autres
Publié: (2026)

Stochastic Langevin Differential Inclusions with Applications to Machine Learning
par: Difonzo, Fabio V., et autres
Publié: (2022)

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics
par: Paulin, Daniel, et autres
Publié: (2024)

When Langevin Monte Carlo Meets Randomization: New Sampling Algorithms with Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness
par: Wang, Xiaojie, et autres
Publié: (2025)

Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
par: Zhang, Borong, et autres
Publié: (2024)

A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellations
par: Gomez, Alvaro Almeida
Publié: (2025)

A Discrete Neural Operator with Adaptive Sampling for Surrogate Modeling of Parametric Transient Darcy Flows in Porous Media
par: Chen, Zhenglong, et autres
Publié: (2025)

Nonlinear Assimilation via Score-based Sequential Langevin Sampling
par: Ding, Zhao, et autres
Publié: (2024)

Discrete Differential Principle for Continuous Smooth Function Representation
par: Wang, Guoyou, et autres
Publié: (2025)

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
par: Jalalian, Yasamin, et autres
Publié: (2025)

Provably Faster Gradient Descent via Long Steps
par: Grimmer, Benjamin
Publié: (2023)

Physics-informed Discretization-independent Deep Compositional Operator Network
par: Zhong, Weiheng, et autres
Publié: (2024)

Trust-Region Methods with Low-Fidelity Objective Models
par: Angino, Andrea, et autres
Publié: (2025)

A Discrete Perspective Towards the Construction of Sparse Probabilistic Boolean Networks
par: Fok, Christopher H., et autres
Publié: (2024)

Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
par: Subedi, Unique, et autres
Publié: (2024)

Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling
par: Špetlík, Martin, et autres
Publié: (2026)

Energy Approach from $\varepsilon$-Graph to Continuum Diffusion Model with Connectivity Functional
par: Yang, Yahong, et autres
Publié: (2025)

Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models
par: Saporiti, Riccardo, et autres
Publié: (2026)

Antithetic Noise in Diffusion Models
par: Jia, Jing, et autres
Publié: (2025)

Convergence of Kinetic Langevin Monte Carlo on Lie groups
par: Kong, Lingkai, et autres
Publié: (2024)

A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
par: Lan, Kai Weixian, et autres
Publié: (2023)