Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support
cs.LG, stat.ML
Submitted: 2026-09-30
Updated: 2026-09-30
Comments: 66 pages, 0 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
- Error Bounds for Flow Matching Methods
- SE(3)-Stochastic Flow Matching for Protein Backbone Generation
- Flow Matching on General Geometries
- Convergence of denoising diffusion models under the manifold hypothesis
- Flow matching achieves almost minimax optimal convergence
- Gaussian Interpolation Flows
- GSURE-Based Diffusion Model Training with Corrupted Data
- Flow Matching is Adaptive to Manifold Structures
- On the minimax optimality of Flow Matching through the connection to kernel density estimation
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Generalization error bound for denoising score matching under relaxed manifold assumption
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks