Cover Image

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Farghly, Tyler, Rebeschini, Patrick, Deligiannidis, George, Doucet, Arnaud
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Generalisation under gradient descent via deterministic PAC-Bayes
by: Clerico, Eugenio, et al.
Published: (2022)

Linear Convergence of Diffusion Models Under the Manifold Hypothesis
by: Potaptchik, Peter, et al.
Published: (2024)

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
by: Azangulov, Iskander, et al.
Published: (2024)

Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression
by: Wegel, Tobias, et al.
Published: (2025)

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
by: Alfano, Carlo, et al.
Published: (2023)

Error Bounds for Flow Matching Methods
by: Benton, Joe, et al.
Published: (2023)

Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
by: Benton, Joe, et al.
Published: (2023)

Metropolis-Adjusted Diffusion Models
by: Lam, Kevin H., et al.
Published: (2026)

Ranking In Generalized Linear Bandits
by: Shidani, Amitis, et al.
Published: (2022)

From Denoising Diffusions to Denoising Markov Models
by: Benton, Joe, et al.
Published: (2022)

Beyond Real Data: Synthetic Data through the Lens of Regularization
by: Shidani, Amitis, et al.
Published: (2025)

Adaptation to Intrinsic Dependence in Diffusion Language Models
by: Zhao, Yunxiao, et al.
Published: (2026)

Differentiable Cost-Parameterized Monge Map Estimators
by: Howard, Samuel, et al.
Published: (2024)

On-Average Stability of Multipass Preconditioned SGD and Effective Dimension
by: Vary, Simon, et al.
Published: (2026)

Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
by: Mildner, Terje, et al.
Published: (2025)

Dependent Latent Class Models
by: Bowers, Jesse, et al.
Published: (2022)

Manifold Learning with Sparse Regularised Optimal Transport
by: Zhang, Stephen, et al.
Published: (2023)

Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
by: Fu, Hengyu, et al.
Published: (2024)

Analysis of Diffusion Models for Manifold Data
by: George, Anand Jerry, et al.
Published: (2025)

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
by: Liang, Jiaming, et al.
Published: (2024)

Implicit Regularization Paths of Weighted Neural Representations
by: Du, Jin-Hong, et al.
Published: (2024)

An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
by: Huang, Xunpeng, et al.
Published: (2024)

On Reconstructing Training Data From Bayesian Posteriors and Trained Models
by: Wynne, George
Published: (2025)

Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
by: Peng, Liangzu, et al.
Published: (2026)

Algebraic Geometrical Analysis of Metropolis Algorithm When Parameters Are Non-identifiable
by: Nagata, Kenji, et al.
Published: (2024)

Beyond Scores: Proximal Diffusion Models
by: Fang, Zhenghan, et al.
Published: (2025)

Generalising realisability in statistical learning theory under epistemic uncertainty
by: Cuzzolin, Fabio
Published: (2024)

Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets
by: Yu, Zixiong, et al.
Published: (2024)

Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
by: Di Gregorio, Simone, et al.
Published: (2025)

Central Limit Theorem for Bayesian Neural Network trained with Variational Inference
by: Descours, Arnaud, et al.
Published: (2024)

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

Statistical Convergence of Spherical First Hitting Diffusion Models
by: Bienewald, Simon, et al.
Published: (2026)

Dimension-free Score Matching and Time Bootstrapping for Diffusion Models
by: Kumar, Syamantak, et al.
Published: (2025)

Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
by: Li, Gen, et al.
Published: (2025)

Nearest-Neighbor Radii under Dependent Sampling
by: Gao, Yuanyuan, et al.
Published: (2026)

On the Limitation of Kernel Dependence Maximization for Feature Selection
by: Liu, Keli, et al.
Published: (2024)

Implicit score matching meets denoising score matching: improved rates of convergence and log-density Hessian estimation
by: Yakovlev, Konstantin, et al.
Published: (2025)

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
by: Pedrotti, Francesco, et al.
Published: (2023)

An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
by: Chen, Minshuo, et al.
Published: (2024)