ott.neural

In contrast to most methods presented in ott.solvers, which output vectors or matrices, the goal of the ott.neural module is to parameterize optimal transport maps and couplings as neural networks. These neural networks can generalize to new samples, in the sense that they can be conveniently evaluated outside training samples. This module implements layers, models and solvers to estimate such neural networks.

• ott.neural.datasets
  • Datasets
• ott.neural.methods
  • Monge Gap
  • Neural Dual
• ott.neural.methods.flows
  • Flows
• ott.neural.networks
  • Networks
• ott.neural.networks.layers
  • Layers