Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
arXiv:2007.04462
Abstract
Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport. In this work, we present a novel scalable algorithm to approximate the Wasserstein Barycenters aiming at high-dimensional applications in machine learning. Our proposed algorithm is based on the Kantorovich dual formulation of the Wasserstein-2 distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. The distinguishing features of our method are: i) it only requires samples from the marginal distributions; ii) unlike the existing approaches, it represents the Barycenter with a generative model and can thus generate infinite samples from the barycenter without querying the marginal distributions; iii) it works similar to Generative Adversarial Model in one marginal case. We demonstrate the efficacy of our algorithm by comparing it with the state-of-art methods in multiple experiments.
21 pages
References in corpus (5)
- 2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs
- Continuous Regularized Wasserstein Barycenters
- Adversarial Computation of Optimal Transport Maps
- On Scalable and Efficient Computation of Large Scale Optimal Transport
- Variational Wasserstein Barycenters for Geometric Clustering
Cited by in corpus (9)
- Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey
- Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
- Large-Scale Wasserstein Gradient Flows
- Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization
- Learning High Dimensional Wasserstein Geodesics
- Barycentric-alignment and reconstruction loss minimization for domain generalization
- Neural Monge Map estimation and its applications
- Variational Wasserstein Barycenters with c-Cyclical Monotonicity
- Input Convex Gradient Networks