Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kandasamy, Saravanan, Nagaraj, Dheeraj
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Numerical Analysis
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
by: Srinivasan, Rishikesh, et al.
Published: (2025)

How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework
by: Ren, Yinuo, et al.
Published: (2024)

Distillation of Discrete Diffusion through Dimensional Correlations
by: Hayakawa, Satoshi, et al.
Published: (2024)

Constrained Ensemble Langevin Monte Carlo
by: Ding, Zhiyan, et al.
Published: (2021)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
by: Zhan, Zhiyuan, et al.
Published: (2026)

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

Provable Diffusion Posterior Sampling for Bayesian Inversion
by: Chang, Jinyuan, et al.
Published: (2025)

Second Order Ensemble Langevin Method for Sampling and Inverse Problems
by: Liu, Ziming, et al.
Published: (2022)

Kinetic Langevin Splitting Schemes for Constrained Sampling
by: Chada, Neil K., et al.
Published: (2026)

ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamics
by: Zhu, Xianli, et al.
Published: (2026)

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
by: Dong, Yijun, et al.
Published: (2024)

BrowNNe: Brownian Nonlocal Neurons & Activation Functions
by: Nagaraj, Sriram, et al.
Published: (2024)

Nonlocal Neural Tangent Kernels via Parameter-Space Interactions
by: Nagaraj, Sriram, et al.
Published: (2025)

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
by: Modoranu, Ionut-Vlad, et al.
Published: (2024)

Invertible ResNets for Inverse Imaging Problems: Competitive Performance with Provable Regularization Properties
by: Arndt, Clemens, et al.
Published: (2024)

Solving Poisson Equations using Neural Walk-on-Spheres
by: Nam, Hong Chul, et al.
Published: (2024)

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
by: Zangrando, Emanuele, et al.
Published: (2024)

Localized Diffusion Models
by: Gottwald, Georg A., et al.
Published: (2025)

Learning Epidemiological Dynamics via the Finite Expression Method
by: Du, Jianda, et al.
Published: (2024)

Sampling via Stochastic Interpolants by Langevin-based Velocity and Initialization Estimation in Flow ODEs
by: Duan, Chenguang, et al.
Published: (2026)

Stochastic Langevin Differential Inclusions with Applications to Machine Learning
by: Difonzo, Fabio V., et al.
Published: (2022)

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics
by: Paulin, Daniel, et al.
Published: (2024)

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

Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
by: Zhang, Borong, et al.
Published: (2024)

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

A Discrete Neural Operator with Adaptive Sampling for Surrogate Modeling of Parametric Transient Darcy Flows in Porous Media
by: Chen, Zhenglong, et al.
Published: (2025)

Nonlinear Assimilation via Score-based Sequential Langevin Sampling
by: Ding, Zhao, et al.
Published: (2024)

Discrete Differential Principle for Continuous Smooth Function Representation
by: Wang, Guoyou, et al.
Published: (2025)

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
by: Jalalian, Yasamin, et al.
Published: (2025)

Provably Faster Gradient Descent via Long Steps
by: Grimmer, Benjamin
Published: (2023)

Physics-informed Discretization-independent Deep Compositional Operator Network
by: Zhong, Weiheng, et al.
Published: (2024)

Trust-Region Methods with Low-Fidelity Objective Models
by: Angino, Andrea, et al.
Published: (2025)

A Discrete Perspective Towards the Construction of Sparse Probabilistic Boolean Networks
by: Fok, Christopher H., et al.
Published: (2024)

Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
by: Subedi, Unique, et al.
Published: (2024)

Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling
by: Špetlík, Martin, et al.
Published: (2026)

Energy Approach from $\varepsilon$-Graph to Continuum Diffusion Model with Connectivity Functional
by: Yang, Yahong, et al.
Published: (2025)

Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models
by: Saporiti, Riccardo, et al.
Published: (2026)

Antithetic Noise in Diffusion Models
by: Jia, Jing, et al.
Published: (2025)

Convergence of Kinetic Langevin Monte Carlo on Lie groups
by: Kong, Lingkai, et al.
Published: (2024)

A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
by: Lan, Kai Weixian, et al.
Published: (2023)