Stability of the Kim--Milman flow map
Sinho Chewi, Aram-Alexandre Pooladian, Matthew S. Zhang
TL;DR
This paper characterizes the stability of the Kim--Milman flow map, also known as the probability flow ODE, focusing on how it responds to changes in the target measure measured by relative Fisher information.
Contribution
It provides a new stability analysis of the Kim--Milman flow map with respect to variations in the target measure using relative Fisher information.
Findings
Stability of the Kim--Milman flow map is characterized in terms of relative Fisher information.
The results offer insights into the robustness of the probability flow ODE under measure perturbations.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.