Distributional sliced-Wasserstein and applications to generative modeling
Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-
SW), have been used widely in the recent years due to their fast computation and scalability …
SW), have been used widely in the recent years due to their fast computation and scalability …
Sinkhorn autoencoders
Optimal transport offers an alternative to maximum likelihood for learning generative
autoencoding models. We show that minimizing the $ p $-Wasserstein distance between the …
autoencoding models. We show that minimizing the $ p $-Wasserstein distance between the …
Sliced wasserstein generative models
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to
measure the discrepancy between generated and real data distributions. Unfortunately, it is …
measure the discrepancy between generated and real data distributions. Unfortunately, it is …
Adversarial autoencoders for compact representations of 3D point clouds
Deep generative architectures provide a way to model not only images but also complex, 3-
dimensional objects, such as point clouds. In this work, we present a novel method to obtain …
dimensional objects, such as point clouds. In this work, we present a novel method to obtain …
Tree-sliced variants of Wasserstein distances
Optimal transport (\OT) theory defines a powerful set of tools to compare probability
distributions.\OT~ suffers however from a few drawbacks, computational and statistical …
distributions.\OT~ suffers however from a few drawbacks, computational and statistical …
f-gail: Learning f-divergence for generative adversarial imitation learning
Imitation learning (IL) aims to learn a policy from expert demonstrations that minimizes the
discrepancy between the learner and expert behaviors. Various imitation learning …
discrepancy between the learner and expert behaviors. Various imitation learning …
A survey on optimal transport for machine learning: Theory and applications
LC Torres, LM Pereira, MH Amini - arXiv preprint arXiv:2106.01963, 2021 - arxiv.org
Optimal Transport (OT) theory has seen an increasing amount of attention from the computer
science community due to its potency and relevance in modeling and machine learning. It …
science community due to its potency and relevance in modeling and machine learning. It …
Wasserstein unsupervised reinforcement learning
Unsupervised reinforcement learning aims to train agents to learn a handful of policies or
skills in environments without external reward. These pre-trained policies can accelerate …
skills in environments without external reward. These pre-trained policies can accelerate …
On the convergence of coordinate ascent variational inference
As a computational alternative to Markov chain Monte Carlo approaches, variational
inference (VI) is becoming more and more popular for approximating intractable posterior …
inference (VI) is becoming more and more popular for approximating intractable posterior …
[PDF][PDF] Generalized variational inference
This paper introduces a generalized representation of Bayesian inference. It is derived
axiomatically, recovering existing Bayesian methods as special cases. We then use it to …
axiomatically, recovering existing Bayesian methods as special cases. We then use it to …