Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates

arXiv:2610.01193 · cs.LG, cs.AI, math.ST, stat.ML, stat.TH · Submitted 2026-10-01 · Read on arXiv

cs.LG, cs.AI, math.ST, stat.ML, stat.TH

Submitted: 2026-10-01

Updated: 2026-10-01

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 17× in this paper · explained in 1 episode
• Flow Matching — 15× in this paper · explained in 8 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Generalization — 8× in this paper · explained in 13 episodes
• Diffusion Model — 6× in this paper · explained in 8 episodes
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Optimal Transport — 5× in this paper · explained in 5 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Wasserstein Distance — 3× in this paper · explained in 4 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Sample Complexity — 2× in this paper · explained in 15 episodes
• Selection Bias — 2× in this paper · explained in 4 episodes
• Approximation Bound — 1× in this paper · explained in 1 episode
• Causal Inference — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Diffusion Processes — 1× in this paper · explained in 2 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Minimax optimality — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Stochastic Dynamics — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Minimax Optimality of the Probability Flow ODE for Diffusion Models
• Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks
• Debiased Counterfactual Generation via Flow Matching from Observations
• Total Variation Rates for Riemannian Flow Matching
• Optimal Convergence Analysis of DDPM for General Distributions
• DoubleGen: Debiased Generative Modeling of Counterfactuals
• Entropic estimation of optimal transport maps
• Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities
• On Flow Matching KL Divergence
• Elucidating Rectified Flow with Deterministic Sampler: Polynomial Discretization Complexity for Multi and One-step Models
• Sublinear iterations can suffice even for DDPMs

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