Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …

We present rectified flow, a surprisingly simple approach to learning (neural) ordinary
differential equation (ODE) models to transport between two empirically observed …

Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …

Optimal transport has recently been reintroduced to the machine learning community thanks
in part to novel efficient optimization procedures allowing for medium to large scale …

Simulation-free methods for training continuous-time generative models construct probability
paths that go between noise distributions and individual data samples. Recent works, such …

In computer vision, one is often confronted with problems of domain shifts, which occur when
one applies a classifier trained on a source dataset to target data sharing similar …

Estimating individual treatment effects from observational data is challenging due to
treatment selection bias. Prevalent methods mainly mitigate this issue by aligning different …

Unsupervised domain adaptation (UDA) is a representative problem in transfer learning,
which aims to improve the classification performance on an unlabeled target domain by …

In this paper, we present a novel and principled approach to learn the optimal transport
between two distributions, from samples. Guided by the optimal transport theory, we learn …

We present a novel neural-networks-based algorithm to compute optimal transport maps
and plans for strong and weak transport costs. To justify the usage of neural networks, we …