Learning Cost Functions for Optimal Transport
arXiv:2002.09650
Abstract
Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive an unconstrained convex optimization formulation of the inverse OT problem, which can be further augmented by any customizable regularization. We provide a comprehensive characterization of the properties of inverse OT, including uniqueness of solutions. We also develop two numerical algorithms, one is a fast matrix scaling method based on the Sinkhorn-Knopp algorithm for discrete OT, and the other one is a learning based algorithm that parameterizes the cost function as a deep neural network for continuous OT. The novel framework proposed in the work avoids repeatedly solving a forward OT in each iteration which has been a thorny computational bottleneck for the bi-level optimization in existing inverse OT approaches. Numerical results demonstrate promising efficiency and accuracy advantages of the proposed algorithms over existing state-of-the-art methods.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- A Survey on Metric Learning for Feature Vectors and Structured Data
- Personality Traits and the Marriage Market
- Stochastic Optimization for Large-scale Optimal Transport
- Ground Metric Learning
- Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form
- Regularized Optimal Transport is Ground Cost Adversarial
- Learning to Match via Inverse Optimal Transport
- Geometry of Graph Partitions via Optimal Transport
- Learning transport cost from subset correspondence