Rectified Flow: A Marginal Preserving Approach to Optimal Transport
This work addresses the optimal transport problem for researchers in machine learning and optimization, offering a novel interior approach that is incremental compared to existing methods.
The paper tackles the optimal transport problem between two continuous distributions by minimizing a specific transport cost while preserving marginal constraints, introducing a flow-based method that iteratively reduces the cost through neural ODEs and achieves monotonic improvement.
We present a flow-based approach to the optimal transport (OT) problem between two continuous distributions $π_0,π_1$ on $\mathbb{R}^d$, of minimizing a transport cost $\mathbb{E}[c(X_1-X_0)]$ in the set of couplings $(X_0,X_1)$ whose marginal distributions on $X_0,X_1$ equals $π_0,π_1$, respectively, where $c$ is a cost function. Our method iteratively constructs a sequence of neural ordinary differentiable equations (ODE), each learned by solving a simple unconstrained regression problem, which monotonically reduce the transport cost while automatically preserving the marginal constraints. This yields a monotonic interior approach that traverses inside the set of valid couplings to decrease the transport cost, which distinguishes itself from most existing approaches that enforce the coupling constraints from the outside. The main idea of the method draws from rectified flow, a recent approach that simultaneously decreases the whole family of transport costs induced by convex functions $c$ (and is hence multi-objective in nature), but is not tailored to minimize a specific transport cost. Our method is a single-object variant of rectified flow that guarantees to solve the OT problem for a fixed, user-specified convex cost function $c$.