Learning Cost Functions for Optimal Transport

02/22/2020
by   Haodong Sun, et al.
10

Learning the cost function for optimal transport from observed transport plan or its samples has been cast as a bi-level optimization problem. In this paper, we derive an unconstrained convex optimization formulation for the problem which can be further augmented by any customizable regularization. This novel framework avoids repeatedly solving a forward optimal transport problem in each iteration which has been a thorny computational bottleneck for the bi-level optimization approach. To validate the effectiveness of this framework, we develop two numerical algorithms, one is a fast matrix scaling method based on the Sinkhorn-Knopp algorithm for the discrete case, and the other is a supervised learning algorithm that realizes the cost function as a deep neural network in the continuous case. Numerical results demonstrate promising efficiency and accuracy advantages of the proposed algorithms over existing state of the art methods.

READ FULL TEXT
research
02/23/2018

Computation of optimal transport and related hedging problems via penalization and neural networks

This paper presents a widely applicable approach to solving (multi-margi...
research
01/26/2023

Open Problems in Applied Deep Learning

This work formulates the machine learning mechanism as a bi-level optimi...
research
09/29/2019

Learning transport cost from subset correspondence

Learning to align multiple datasets is an important problem with many ap...
research
05/31/2022

On Forward Kinematics of a 3SPR Parallel Manipulator

In this paper, a new numerical method to solve the forward kinematics (F...
research
03/07/2023

New Perspectives on Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimization

We study optimal transport-based distributionally robust optimization pr...
research
01/23/2022

Revisiting Pooling through the Lens of Optimal Transport

Pooling is one of the most significant operations in many machine learni...
research
11/16/2020

Optimal Transport-based Coverage Control for Swarm Robot Systems: Generalization of the Voronoi Tessellation-based Method

Swarm robot systems, which consist of many cooperating mobile robots, ha...

Please sign up or login with your details

Forgot password? Click here to reset