Abstract
In this short note, we characterize stability of the Kim--Milman flow map -- also known as the probability flow ODE -- with respect to variations in the target measure in relative Fisher information.
Stability of the Kim--Milman flow map
Related papers
Ranked by semantic similarity β how closely each paper's abstract matches this one (100% = near-identical topic).
- Distribution estimation via Flow Matching with Lipschitz guarantees (2025)57% match
- Flow matching achieves almost minimax optimal convergence (2024)55% match
- Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation (2026)52% match
- Error Bounds for Flow Matching Methods (2023)52% match
- Asymptotically exact variational flows via involutive MCMC kernels (2025)52% match
- Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation (2022)51% match
- Conditional Flow Matching for Bayesian Posterior Inference (2025)51% match
- Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching (2024)51% match