On Transportation of Mini-batches: A Hierarchical Approach
arXiv:2102.05912
Abstract
Mini-batch optimal transport (m-OT) has been successfully used in practical applications that involve probability measures with a very high number of supports. The m-OT solves several smaller optimal transport problems and then returns the average of their costs and transportation plans. Despite its scalability advantage, the m-OT does not consider the relationship between mini-batches which leads to undesirable estimation. Moreover, the m-OT does not approximate a proper metric between probability measures since the identity property is not satisfied. To address these problems, we propose a novel mini-batch scheme for optimal transport, named Batch of Mini-batches Optimal Transport (BoMb-OT), that finds the optimal coupling between mini-batches and it can be seen as an approximation to a well-defined distance on the space of probability measures. Furthermore, we show that the m-OT is a limit of the entropic regularized version of the BoMb-OT when the regularized parameter goes to infinity. Finally, we carry out experiments on various applications including deep generative models, deep domain adaptation, approximate Bayesian computation, color transfer, and gradient flow to show that the BoMb-OT can be widely applied and performs well in various applications.
Accepted to ICML 2022, 34 pages, 16 figures, 9 tables
References in corpus (10)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
- The Cramer Distance as a Solution to Biased Wasserstein Gradients
- Approximate Bayesian computation with the Wasserstein distance
- Multilevel Clustering via Wasserstein Means
- Minibatch optimal transport distances; analysis and applications
- Continuous Regularized Wasserstein Barycenters
- Adversarial Computation of Optimal Transport Maps
- Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
- Hierarchical Optimal Transport for Robust Multi-View Learning