Imagen de Portada

Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chakraborty, Saptarshi, Berthet, Quentin, Bartlett, Peter L.
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
por: Chakraborty, Saptarshi, et al.
Publicado: (2024)

A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data
por: Chakraborty, Saptarshi, et al.
Publicado: (2024)

A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
por: Chakraborty, Saptarshi, et al.
Publicado: (2024)

A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data
por: Chakraborty, Saptarshi, et al.
Publicado: (2024)

Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
por: Roy, Saptarshi, et al.
Publicado: (2026)

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
por: Li, Gen, et al.
Publicado: (2024)

Scaling Laws in Linear Regression: Compute, Parameters, and Data
por: Lin, Licong, et al.
Publicado: (2024)

A Score-Based Density Formula, with Applications in Diffusion Generative Models
por: Li, Gen, et al.
Publicado: (2024)

Neural Networks Generalize on Low Complexity Data
por: Chatterjee, Sourav, et al.
Publicado: (2024)

Cyclic Counterfactuals under Shift-Scale Interventions
por: Saha, Saptarshi, et al.
Publicado: (2025)

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
por: Farghly, Tyler, et al.
Publicado: (2025)

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
por: Mei, Song
Publicado: (2024)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
por: Su, Xun, et al.
Publicado: (2025)

O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions
por: Li, Gen, et al.
Publicado: (2024)

On the Statistical Capacity of Deep Generative Models
por: Tam, Edric, et al.
Publicado: (2025)

Counterfactual Generative Modeling with Variational Causal Inference
por: Wu, Yulun, et al.
Publicado: (2024)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
por: Wang, Kevin, et al.
Publicado: (2026)

Diffusion Posterior Sampling is Computationally Intractable
por: Gupta, Shivam, et al.
Publicado: (2024)

Training Implicit Generative Models via an Invariant Statistical Loss
por: de Frutos, José Manuel, et al.
Publicado: (2024)

A Diffusion Analysis of Policy Gradient for Stochastic Bandits
por: Lattimore, Tor
Publicado: (2026)

On the Separability of Information in Diffusion Models
por: Premkumar, Akhil
Publicado: (2025)

Towards Bayesian Data Selection
por: Rodemann, Julian
Publicado: (2024)

FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits
por: Chakraborty, Sunrit, et al.
Publicado: (2024)

Improved Scaling Laws in Linear Regression via Data Reuse
por: Lin, Licong, et al.
Publicado: (2025)

Compression, Generalization and Learning
por: Campi, Marco C., et al.
Publicado: (2023)

Convergence of Shallow ReLU Networks on Weakly Interacting Data
por: Dana, Léo, et al.
Publicado: (2025)

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters
por: Kratsios, Anastasis, et al.
Publicado: (2025)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
por: Firdoussi, Aymane El, et al.
Publicado: (2024)

Generalization and Scaling Laws for Mixture-of-Experts Transformers
por: Mayaki, Mansour Zoubeirou a
Publicado: (2026)

Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
por: Zhang, Bohan, et al.
Publicado: (2025)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
por: Frei, Spencer, et al.
Publicado: (2022)

A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
por: Hazard, Christopher J., et al.
Publicado: (2025)

Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs
por: Dong, Zihan, et al.
Publicado: (2026)

A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
por: Kumar, Shivam, et al.
Publicado: (2024)

Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data
por: Cribeiro-Ramallo, Jose, et al.
Publicado: (2025)

A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
por: Yu, Hao
Publicado: (2026)

On the Provable Performance Guarantee of Efficient Reasoning Models
por: Zeng, Hao, et al.
Publicado: (2025)

Foundations of Top-$k$ Decoding For Language Models
por: Noarov, Georgy, et al.
Publicado: (2025)

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
por: Yu, Hao
Publicado: (2025)

Cross-regularization: Adaptive Model Complexity through Validation Gradients
por: Brito, Carlos Stein
Publicado: (2025)