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 …

Despite the recent popularity of neural network-based solvers for optimal transport (OT),
there is no standard quantitative way to evaluate their performance. In this paper, we …

Abstract Wasserstein Generative Adversarial Networks (WGANs) are the popular generative
models built on the theory of Optimal Transport (OT) and the Kantorovich duality. Despite the …

To measure the difference between two probability distributions, referred to as the source
and target, respectively, we exploit both the chain rule and Bayes' theorem to construct …

Abstract Wasserstein GANs with Gradient Penalty (WGAN-GP) are a very popular method for
training generative models to produce high quality synthetic data. While WGAN-GP were …

Individual Treatment Effects (ITE) estimation methods have risen in popularity in the last
years. Most of the time, individual effects are better presented as Conditional Average …

Generative adversarial networks (GANs) have turned up as the most widely used
approaches for creating realistic samples. They're the effective latent variable models for …

Abstract Generative Adversarial Networks (GANs) are a method for producing a distribution
μ that one can sample which approximates a distribution ν of real data. Wasserstein GANs …

The recent progress of deep learning has enabled more powerful frameworks to create good-
quality deepfakes. Deepfakes, which are mostly known for malicious purposes, have great …

[ES] Las redes generativas adversarias (GANs) han supuesto un gran avance en el campo
de los modelos generativos de aprendizaje profundo. Estas son dos redes neuronales que …