Efficient estimates of optimal transport via low-dimensional embeddings
arXiv:2111.04838
Abstract
Optimal transport distances (OT) have been widely used in recent work in Machine Learning as ways to compare probability distributions. These are costly to compute when the data lives in high dimension. Recent work by Paty et al., 2019, aims specifically at reducing this cost by computing OT using low-rank projections of the data (seen as discrete measures). We extend this approach and show that one can approximate OT distances by using more general families of maps provided they are 1-Lipschitz. The best estimate is obtained by maximising OT over the given family. As OT calculations are done after mapping data to a lower dimensional space, our method scales well with the original data dimension. We demonstrate the idea with neural networks.
arXiv commentNeurips 2021 Optimal Transport and Machine Learning Workshop
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Fast Computation of Wasserstein Barycenters
- Spectral Norm Regularization for Improving the Generalizability of Deep Learning
- Sample Complexity of Sinkhorn divergences
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
- Stochastic Wasserstein Barycenters
- Statistical Optimal Transport via Factored Couplings
- Wasserstein Training of Boltzmann Machines
- Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections