Gaussian-Channel Regularity and Distribution Learning with Flow Matching
stat.ML, cs.LG
Submitted: 2024-03-31
Updated: 2026-11-16
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
- Deep conditional distribution learning via conditional F"ollmer flow
- Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks
- Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
- Analysis of learning a flow-based generative model from limited sample complexity
- Lipschitz Transport Maps via the Follmer Flow
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Gaussian Interpolation Flows
- Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models
- Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
- Conditional Stochastic Interpolation for Generative Learning
- SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
- Distribution learning via neural differential equations: a nonparametric statistical perspective
- The Brownian transport map
- Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
- Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks
- Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Models
- Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference