Copertina

The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schaeffer, Bernardo P., Rosa, Ricardo M. S., Valle, Glauco
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training Neural Samplers with Reverse Diffusive KL Divergence
di: He, Jiajun, et al.
Pubblicazione: (2024)

Adaptive Symmetrization of the KL Divergence
di: Ben-Dov, Omri, et al.
Pubblicazione: (2025)

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

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
di: Aminian, Gholamali, et al.
Pubblicazione: (2025)

On the KL-Divergence-based Robust Satisficing Model
di: Yan, Haojie, et al.
Pubblicazione: (2024)

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
di: Xie, Zhijie, et al.
Pubblicazione: (2022)

Sampling, Diffusions, and Stochastic Localization
di: Montanari, Andrea
Pubblicazione: (2023)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
di: Yuan, Rui, et al.
Pubblicazione: (2026)

On Flow Matching KL Divergence
di: Su, Maojiang, et al.
Pubblicazione: (2025)

Controlled Latent Diffusion Models for 3D Porous Media Reconstruction
di: Naiff, Danilo, et al.
Pubblicazione: (2025)

Optimal Stability of KL Divergence under Gaussian Perturbations
di: Pan, Jialu, et al.
Pubblicazione: (2026)

Deterministic Dynamics of Sampling Processes in Score-Based Diffusion Models with Multiplicative Noise Conditioning
di: Kim, Doheon
Pubblicazione: (2026)

Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence
di: Datar, Adwait, et al.
Pubblicazione: (2025)

How Scale Breaks "Normalized Stress" and KL Divergence: Rethinking Quality Metrics
di: Smelser, Kiran, et al.
Pubblicazione: (2025)

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
di: Zhu, Lingwei, et al.
Pubblicazione: (2023)

Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
di: Schaeffer, Rylan, et al.
Pubblicazione: (2025)

Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations
di: Abyaneh, Amin, et al.
Pubblicazione: (2026)

Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
di: Xu, Yanbo, et al.
Pubblicazione: (2025)

KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective
di: Muñoz, Andrés, et al.
Pubblicazione: (2026)

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
di: Zhang, Shiyuan, et al.
Pubblicazione: (2026)

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

Revisiting Score Function Estimators for $k$-Subset Sampling
di: Wijk, Klas, et al.
Pubblicazione: (2024)

Towards Fast Stochastic Sampling in Diffusion Generative Models
di: Pandey, Kushagra, et al.
Pubblicazione: (2024)

Implicit Diffusion: Efficient Optimization through Stochastic Sampling
di: Marion, Pierre, et al.
Pubblicazione: (2024)

What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
di: Azeglio, Simone, et al.
Pubblicazione: (2025)

Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
di: Zhang, Zikun, et al.
Pubblicazione: (2024)

Shifted Composition III: Local Error Framework for KL Divergence
di: Altschuler, Jason M., et al.
Pubblicazione: (2024)

Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks
di: Cinquin, Tristan, et al.
Pubblicazione: (2024)

Forward $χ^2$ Divergence Based Variational Importance Sampling
di: Li, Chengrui, et al.
Pubblicazione: (2023)

Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
di: Li, Runjia, et al.
Pubblicazione: (2024)

Tight Bounds on the Binomial CDF, and the Minimum of i.i.d Binomials, in terms of KL-Divergence
di: Zhu, Xiaohan, et al.
Pubblicazione: (2025)

Score-based Diffusion Models via Stochastic Differential Equations -- a Technical Tutorial
di: Tang, Wenpin, et al.
Pubblicazione: (2024)

SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
di: Xue, Shuchen, et al.
Pubblicazione: (2023)

A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
di: Su, Junwei, et al.
Pubblicazione: (2025)

Sample-optimal classical shadows for pure states
di: Grier, Daniel, et al.
Pubblicazione: (2022)

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

Gradient-Free Score-Based Sampling Methods with Ensembles
di: Riel, Bryan, et al.
Pubblicazione: (2024)

On the Interpolation Effect of Score Smoothing in Diffusion Models
di: Chen, Zhengdao
Pubblicazione: (2025)

Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
di: Sharrock, Louis, et al.
Pubblicazione: (2022)

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
di: Zhang, Yixian, et al.
Pubblicazione: (2025)