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 …

We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets
minimizing a new metric measuring the distance between the generator distribution and the …

Wasserstein distance plays increasingly important roles in machine learning, stochastic
programming and image processing. Major efforts have been under way to address its high …

This paper introduces a new nonlinear dictionary learning method for histograms in the
probability simplex. The method leverages optimal transport theory, in the sense that our aim …

We propose a novel Wasserstein method with a distillation mechanism, yielding joint
learning of word embeddings and topics. The proposed method is based on the fact that the …

We propose a new method to estimate Wasserstein distances and optimal transport plans
between two probability distributions from samples in high dimension. Unlike plug-in rules …

In this paper, we study the task of visual-text retrieval in the highly practical setting in which
labelled visual data with paired text descriptions are available in one domain (the" source") …

This short article revisits some of the ideas introduced in arXiv: 1701.07875 and arXiv:
1705.07642 in a simple setup. This sheds some lights on the connexions between …

The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence,
has recently gained popularity in machine learning and statistics, as it makes feasible the …

Deep neural networks have established as a powerful tool for large scale supervised
classification tasks. The state-of-the-art performances of deep neural networks are …