On the Equivalence of Optimal Transport Problem and Action Matching with Optimal Vector Fields
This work provides a theoretical link between Flow Matching and Action Matching for generative modeling, but it appears incremental as it builds on existing methods without introducing new paradigms.
The paper demonstrates that using optimal vector fields from Optimal Transport in Flow Matching leads to Optimal Transport in Action Matching, connecting two generative modeling approaches.
Flow Matching (FM) method in generative modeling maps arbitrary probability distributions by constructing an interpolation between them and then learning the vector field that defines ODE for this interpolation. Recently, it was shown that FM can be modified to map distributions optimally in terms of the quadratic cost function for any initial interpolation. To achieve this, only specific optimal vector fields, which are typical for solutions of Optimal Transport (OT) problems, need to be considered during FM loss minimization. In this note, we show that considering only optimal vector fields can lead to OT in another approach: Action Matching (AM). Unlike FM, which learns a vector field for a manually chosen interpolation between given distributions, AM learns the vector field that defines ODE for an entire given sequence of distributions.