Image de couverture de livre

Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	He, Ye, Qiu, Yitong, Tao, Molei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Numerical Analysis Probability
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
par: Krach, Florian, et autres
Publié: (2022)

Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework
par: Andersson, William, et autres
Publié: (2023)

Scale-Adaptive Generative Flows for Multiscale Scientific Data
par: Chen, Yifan, et autres
Publié: (2025)

Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
par: Iske, Meira, et autres
Publié: (2026)

Accelerating Multilevel Markov Chain Monte Carlo Using Machine Learning Models
par: Reddy, Sohail, et autres
Publié: (2024)

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

New Trends in the Stability of Sinkhorn Semigroups
par: Del Moral, Pierre, et autres
Publié: (2026)

Convex-Geometric Error Bounds for Positive-Weight Kernel Quadrature
par: Hayakawa, Satoshi
Publié: (2026)

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

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

Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws
par: Dakhmouche, Ramzi, et autres
Publié: (2025)

Solving stochastic partial differential equations using neural networks in the Wiener chaos expansion
par: Neufeld, Ariel, et autres
Publié: (2024)

Deep learning based numerical approximation algorithms for stochastic partial differential equations
par: Beck, Christian, et autres
Publié: (2020)

Convergence rates for gradient descent in the training of overparameterized artificial neural networks with piecewise affine activation
par: Jentzen, Arnulf, et autres
Publié: (2021)

Correction to "Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations"
par: Paulin, Daniel, et autres
Publié: (2024)

Multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation overcome the curse of dimensionality when approximating semilinear parabolic partial differential equations in $L^p$-sense
par: Neufeld, Ariel, et autres
Publié: (2024)

Modified Equations for Stochastic Optimization
par: Perko, Stefan
Publié: (2025)

A Mean Field Ansatz for Zero-Shot Weight Transfer
par: Chen, Xingyuan, et autres
Publié: (2024)

Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
par: Zhang, Rui, et autres
Publié: (2023)

Unified Stochastic Framework for Neural Network Quantization and Pruning
par: Zhang, Haoyu, et autres
Publié: (2024)

DeepMartingale: Duality of the Optimal Stopping Problem with Expressivity and High-Dimensional Hedging
par: Ye, Junyan, et autres
Publié: (2025)

Quantitative Convergences of Lie Group Momentum Optimizers
par: Kong, Lingkai, et autres
Publié: (2024)

Generalization Bounds for Sparse Random Feature Expansions
par: Hashemi, Abolfazl, et autres
Publié: (2021)

Data-driven approximation of transfer operators for mean-field stochastic differential equations
par: Ioannou, Eirini, et autres
Publié: (2025)

Space-time deep neural network approximations for high-dimensional partial differential equations
par: Hornung, Fabian, et autres
Publié: (2020)

SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
par: Wei, Lifu, et autres
Publié: (2026)

Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped
par: Kim, Kyurae, et autres
Publié: (2025)

Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation
par: Chen, Yifan, et autres
Publié: (2024)

Single-seed generation of Brownian paths and integrals for adaptive and high order SDE solvers
par: Jelinčič, Andraž, et autres
Publié: (2024)

Neural Operators Can Play Dynamic Stackelberg Games
par: Alvarez, Guillermo, et autres
Publié: (2024)

MAD: Manifold Attracted Diffusion
par: Elbrächter, Dennis, et autres
Publié: (2025)

Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
par: Wang, Chenyang, et autres
Publié: (2026)

Numerical and statistical analysis of NeuralODE with Runge-Kutta time integration
par: Ehrhardt, Emily C., et autres
Publié: (2025)

Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
par: He, Ye, et autres
Publié: (2024)

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

Samplet limits and multiwavelets
par: Giacchi, Gianluca, et autres
Publié: (2026)

Constrained Density Estimation via Optimal Transport
par: Hu, Yinan, et autres
Publié: (2026)

Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity
par: Luo, Hengrui, et autres
Publié: (2026)

Gaussian Processes and Reproducing Kernels: Connections and Equivalences
par: Kanagawa, Motonobu, et autres
Publié: (2025)