Image de couverture de livre

Provable Separations between Memorization and Generalization in Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ye, Zeqi, Zhu, Qijie, Tao, Molei, Chen, Minshuo
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
par: Zhu, Qijie, et autres
Publié: (2026)

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
par: Ye, Zeqi, et autres
Publié: (2025)

Provable Statistical Rates for Consistency Diffusion Models
par: Dou, Zehao, et autres
Publié: (2024)

Manifold Generalization Provably Proceeds Memorization in Diffusion Models
par: Shen, Zebang, et autres
Publié: (2026)

What Exactly Does Guidance Do in Masked Discrete Diffusion Models
par: Ye, He, et autres
Publié: (2025)

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
par: Shi, Lianghe, et autres
Publié: (2025)

Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
par: He, Ye, et autres
Publié: (2026)

Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
par: Guo, Wei, et autres
Publié: (2024)

Quantum State Generation with Structure-Preserving Diffusion Model
par: Zhu, Yuchen, et autres
Publié: (2024)

Plug-and-Play Controllable Generation for Discrete Masked Models
par: Guo, Wei, et autres
Publié: (2024)

Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
par: Zhu, Yuchen, et autres
Publié: (2024)

An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
par: Chen, Minshuo, et autres
Publié: (2024)

Counterfactual Generative Models for Time-Varying Treatments
par: Wu, Shenghao, et autres
Publié: (2023)

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
par: Rojas, Kevin, et autres
Publié: (2025)

Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
par: Zhu, Sichen, et autres
Publié: (2025)

Mirror Diffusion Models for Constrained and Watermarked Generation
par: Liu, Guan-Horng, et autres
Publié: (2023)

Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure
par: Chen, Minshuo, et autres
Publié: (2025)

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
par: Jeon, Kijung, et autres
Publié: (2026)

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

Gradient Guidance for Diffusion Models: An Optimization Perspective
par: Guo, Yingqing, et autres
Publié: (2024)

Proximal Diffusion Neural Sampler
par: Guo, Wei, et autres
Publié: (2025)

Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks
par: Xu, Zhenghao, et autres
Publié: (2024)

Generative modeling assisted simulation of measurement-altered quantum criticality
par: Zhu, Yuchen, et autres
Publié: (2024)

TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
par: Tang, Sophia, et autres
Publié: (2025)

Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
par: Zhang, Zixuan, et autres
Publié: (2026)

Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
par: Fu, Hengyu, et autres
Publié: (2024)

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
par: Wu, Yuchen, et autres
Publié: (2024)

On Memorization in Diffusion Models
par: Gu, Xiangming, et autres
Publié: (2023)

Diffusion Model for Data-Driven Black-Box Optimization
par: Li, Zihao, et autres
Publié: (2024)

On the Edge of Memorization in Diffusion Models
par: Buchanan, Sam, et autres
Publié: (2025)

Memorization and Regularization in Generative Diffusion Models
par: Baptista, Ricardo, et autres
Publié: (2025)

Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
par: Shah, Kulin, et autres
Publié: (2025)

Variational Schrödinger Momentum Diffusion
par: Rojas, Kevin, et autres
Publié: (2025)

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
par: Fang, Zhengyu, et autres
Publié: (2024)

Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
par: Zhu, Yuchen, et autres
Publié: (2025)

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
par: Rojas, Kevin, et autres
Publié: (2025)

Evaluating the design space of diffusion-based generative models
par: Wang, Yuqing, et autres
Publié: (2024)

Generalization of Diffusion Models Arises with a Balanced Representation Space
par: Zhang, Zekai, et autres
Publié: (2025)

On the Memorization of Consistency Distillation for Diffusion Models
par: Jiang, Bingqing, et autres
Publié: (2026)

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
par: Zhu, Yuchen, et autres
Publié: (2025)