Cover Image

KL Convergence Guarantees for Score diffusion models under minimal data assumptions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Conforti, Giovanni, Durmus, Alain, Silveri, Marta Gentiloni
Format:	Preprint
Published:	2023
Subjects:	Statistics Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exponential Convergence Guarantees for Iterative Markovian Fitting
by: Silveri, Marta Gentiloni, et al.
Published: (2025)

Theoretical guarantees in KL for Diffusion Flow Matching
by: Silveri, Marta Gentiloni, et al.
Published: (2024)

Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
by: Gentiloni-Silveri, Marta, et al.
Published: (2025)

Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Models
by: Yang, Kaylee Yingxi, et al.
Published: (2022)

Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
by: Pham, Le-Tuyet-Nhi, et al.
Published: (2026)

Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
by: Morisset, Lucas, et al.
Published: (2026)

A Sharp KL-Convergence Analysis for Diffusion Models under Minimal Assumptions
by: Jain, Nishant, et al.
Published: (2025)

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
by: Morisset, Lucas, et al.
Published: (2025)

Generalization error bound for denoising score matching under relaxed manifold assumption
by: Yakovlev, Konstantin, et al.
Published: (2025)

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
by: Liang, Yuchen, et al.
Published: (2025)

Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees
by: Yu, Yifeng, et al.
Published: (2026)

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

Reflected diffusion models adapt to low-dimensional data
by: Holk, Asbjørn, et al.
Published: (2026)

Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent
by: Raj, Gabriel Nixon
Published: (2025)

Score-based sampling without diffusions: Guidance from a simple and modular scheme
by: Wainwright, M. J.
Published: (2025)

Wasserstein KL-divergence for Gaussian distributions
by: Datar, Adwait, et al.
Published: (2025)

Tail-Sensitive KL and Rényi Convergence of Unadjusted Hamiltonian Monte Carlo via One-Shot Couplings
by: Bou-Rabee, Nawaf, et al.
Published: (2026)

Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees
by: Maros, Marie, et al.
Published: (2022)

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

Statistical guarantees for denoising reflected diffusion models
by: Holk, Asbjørn, et al.
Published: (2024)

An Asymptotic Law of the Iterated Logarithm for $\mathrm{KL}_{\inf}$
by: Ram, Ashwin, et al.
Published: (2026)

Towards a unified framework for guided diffusion models
by: Jiao, Yuchen, et al.
Published: (2025)

Regularization can make diffusion models more efficient
by: Taheri, Mahsa, et al.
Published: (2025)

On the convergence of dynamic implementations of Hamiltonian Monte Carlo and No U-Turn Samplers
by: Durmus, Alain, et al.
Published: (2023)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
by: Lytras, Iosif, et al.
Published: (2025)

Score-based generative models are provably robust: an uncertainty quantification perspective
by: Mimikos-Stamatopoulos, Nikiforos, et al.
Published: (2024)

High-accuracy sampling for diffusion models and log-concave distributions
by: Chen, Fan, et al.
Published: (2026)

Frequentist Guarantees of Distributed (Non)-Bayesian Inference
by: Wu, Bohan, et al.
Published: (2023)

Theoretical Guarantees for the Subspace-Constrained Tyler's Estimator
by: Lerman, Gilad, et al.
Published: (2024)

Variational Approach for Efficient KL Divergence Estimation in Dirichlet Mixture Models
by: Pal, Samyajoy, et al.
Published: (2024)

Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions
by: Pham, Le-Tuyet-Nhi, et al.
Published: (2025)

Nonlinear Meta-Learning Can Guarantee Faster Rates
by: Meunier, Dimitri, et al.
Published: (2023)

Statistical Learning Guarantees for Group-Invariant Barron Functions
by: Yang, Yahong, et al.
Published: (2025)

Improved Guarantees for Langevin Monte Carlo with Average Smoothness
by: Dalalyan, Arnak S., et al.
Published: (2026)

Towards a mathematical theory for consistency training in diffusion models
by: Li, Gen, et al.
Published: (2024)

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
by: Zhao, Qingyue, et al.
Published: (2026)

Statistical Guarantees for Approximate Stationary Points of Shallow Neural Networks
by: Taheri, Mahsa, et al.
Published: (2022)

ScoreFusion: Fusing Score-based Generative Models via Kullback-Leibler Barycenters
by: Liu, Hao, et al.
Published: (2024)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
by: Şimşekli, Umut, et al.
Published: (2024)

Optimal Scoring Rule Design under Partial Knowledge
by: Chen, Yiling, et al.
Published: (2021)