Imagen de Portada

Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Yu-Han, Marion, Pierre, Biau, Gérard, Boyer, Claire
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Attention layers provably solve single-location regression
por: Marion, Pierre, et al.
Publicado: (2024)

Optimal Stopping in Latent Diffusion Models
por: Wu, Yu-Han, et al.
Publicado: (2025)

Implicit regularization of deep residual networks towards neural ODEs
por: Marion, Pierre, et al.
Publicado: (2023)

Scaling ResNets in the Large-depth Regime
por: Marion, Pierre, et al.
Publicado: (2022)

Physics-informed kernel learning
por: Doumèche, Nathan, et al.
Publicado: (2024)

Fast kernel methods: Sobolev, physics-informed, and additive models
por: Doumèche, Nathan, et al.
Publicado: (2025)

Convergence Rates for Distribution Matching with Sliced Optimal Transport
por: Thurin, Gauthier, et al.
Publicado: (2026)

A Note on k-NN Gating in RAG
por: Biau, Gérard, et al.
Publicado: (2026)

Forecasting time series with constraints
por: Doumèche, Nathan, et al.
Publicado: (2025)

Attention-based clustering
por: Maulen-Soto, Rodrigo, et al.
Publicado: (2025)

Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
por: Shen, Kaichen, et al.
Publicado: (2025)

Manifold Aware Denoising Score Matching (MAD)
por: Levy-Jurgenson, Alona, et al.
Publicado: (2026)

Sequential Change Point Detection via Denoising Score Matching
por: Zhou, Wenbin, et al.
Publicado: (2025)

What's the score? Automated Denoising Score Matching for Nonlinear Diffusions
por: Singhal, Raghav, et al.
Publicado: (2024)

Efficiently Attacking Memorization Scores
por: Do, Tue, et al.
Publicado: (2025)

On the convergence of PINNs
por: Doumèche, Nathan, et al.
Publicado: (2023)

A Geometry-Aware Residual Correction of Hagan's SABR Implied Volatility Formula
por: Reghai, Adil, et al.
Publicado: (2026)

Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective
por: Boursier, Etienne, et al.
Publicado: (2025)

Understanding diffusion models requires rethinking (again) generalization
por: Marion, Pierre, et al.
Publicado: (2026)

Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
por: George, Anand Jerry, et al.
Publicado: (2025)

Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
por: Livernoche, Victor, et al.
Publicado: (2026)

Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
por: Xu, Tongda
Publicado: (2025)

To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
por: Vargas, Francisco, et al.
Publicado: (2023)

Why Heuristic Weighting Works: A Theoretical Analysis of Denoising Score Matching
por: Zhang, Juyan, et al.
Publicado: (2025)

Concentration Inequalities for Stochastic Optimization of Unbounded Objective Functions with Application to Denoising Score Matching
por: Birrell, Jeremiah
Publicado: (2025)

Memorization Control in Diffusion Models from Denoising-centric Perspective
por: Vu, Thuy Phuong, et al.
Publicado: (2026)

Physics-informed machine learning as a kernel method
por: Doumèche, Nathan, et al.
Publicado: (2024)

Are Large Language Models Memorizing Bug Benchmarks?
por: Ramos, Daniel, et al.
Publicado: (2024)

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
por: Wu, Zhuguanyu, et al.
Publicado: (2026)

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
por: Wu, Jingfeng, et al.
Publicado: (2025)

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
por: Chen, Tianyu, et al.
Publicado: (2025)

CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning
por: Liu, Zeyuan, et al.
Publicado: (2024)

Diffusing States and Matching Scores: A New Framework for Imitation Learning
por: Wu, Runzhe, et al.
Publicado: (2024)

Moment Matching Denoising Gibbs Sampling
por: Zhang, Mingtian, et al.
Publicado: (2023)

Rethinking Memorization Measures and their Implications in Large Language Models
por: Ghosh, Bishwamittra, et al.
Publicado: (2025)

Taking the Road Less Scheduled with Adaptive Polyak Steps
por: Oikonomou, Dimitris, et al.
Publicado: (2025)

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
por: Lin, Runqi, et al.
Publicado: (2023)

Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
por: Schwienhorst, Benedikt Lütke, et al.
Publicado: (2026)

One-Step Diffusion Distillation through Score Implicit Matching
por: Luo, Weijian, et al.
Publicado: (2024)

From the Gradient-Step Denoiser to the Proximal Denoiser and their associated convergent Plug-and-Play algorithms
por: Herfeld, Vincent, et al.
Publicado: (2025)