No article text was recorded for this version.
theoretical convergence guarantees (theoretical-empirical gap in generative modeling)
Version 1 of 129 papers31 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DDPM Score Matching Is Asymptotically Efficient
- Blog: KL Convergence Guarantees for Score Diffusion Models under Minimal Data Assumptions
- Blog: Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions
- Blog: Convergence of score-based generative modeling for general data distributions
- Blog: An Error Analysis of Flow Matching for Deep Generative Modeling
- Blog: Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency
- Blog: Learning (Very) Simple Generative Models Is Hard
- Blog: Diffusion Models are Minimax Optimal Distribution Estimators
- Blog: Diffusion Model for Multiple Antenna Communication
- Blog: An Error Analysis of Flow Matching for Deep Generative Modeling
- Blog: Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation
- Blog: Improved Convergence Rate for Diffusion Probabilistic Models
- Blog: Abstraction of Markov Population Dynamics via Generative Adversarial Nets
- Blog: A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
- Blog: Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable
- Blog: Learning Mixtures of Gaussians Using the DDPM Objective
- Blog: Learning Distributions Generated by One-Layer ReLU Networks
- Blog: Gradient Guidance for Diffusion Models: An Optimization Perspective
- Blog: Adversarial Discrete Sequence Generation without Explicit NeuralNetworks as Discriminators
- Blog: Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
- Blog: A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
- Blog: Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
- Blog: Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation
- Blog: Diffusion Models are Minimax Optimal Distribution Estimators
- Blog: Energy-based diffusion generator for efficient sampling of Boltzmann distributions
- Blog: Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
- Blog: On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
- Blog: Generative Forests
- Blog: Learning Discrete Concepts in Latent Hierarchical Models
History & citation
Current · Permanent link
- This direction split from Convergence Guarantees for Diffusion and Flow Matching (69% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_theoretical_convergence_guarantees_theor_17aea1a6,
title = {theoretical convergence guarantees (theoretical-empirical gap in generative modeling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/theoretical-convergence-guarantees-theoretical-empirical-gap-in-generative/rdr_17aea1a6818a4fc5b1215746a0e0bc3c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_theoretical_convergence_guarantees_theor_17aea1a6_v1,
title = {theoretical convergence guarantees (theoretical-empirical gap in generative modeling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/theoretical-convergence-guarantees-theoretical-empirical-gap-in-generative/rdr_17aea1a6818a4fc5b1215746a0e0bc3c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}