E Heitz, K Vanhoey, T Chambon… - Proceedings of the …, 2021 - openaccess.thecvf.com
We address the problem of computing a textural loss based on the statistics extracted from the feature activations of a convolutional neural network optimized for object recognition (eg …
E Bernton, PE Jacob, M Gerber… - … and Inference: A …, 2019 - academic.oup.com
Statistical inference can be performed by minimizing, over the parameter space, the Wasserstein distance between model distributions and the empirical distribution of the data …
Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a robust variant of the Wasserstein distance. Recent work suggests that this quantity is more …
Frechet means and Procrustes analysis in Wasserstein space Page 1 Bernoulli 25(2), 2019, 932–976 https://doi.org/10.3150/17-BEJ1009 Fréchet means and Procrustes analysis in …
M Huang, S Ma, L Lai - International Conference on …, 2021 - proceedings.mlr.press
The Wasserstein distance has become increasingly important in machine learning and deep learning. Despite its popularity, the Wasserstein distance is hard to approximate because of …
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 …
T Lin, Z Zheng, E Chen, M Cuturi… - International …, 2021 - proceedings.mlr.press
Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the …
Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric …
Abstract The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant …