English

Unbalanced Optimal Transport through Non-negative Penalized Linear Regression

Optimization and Control 2021-06-09 v1 Machine Learning Machine Learning

Abstract

This paper addresses the problem of Unbalanced Optimal Transport (UOT) in which the marginal conditions are relaxed (using weighted penalties in lieu of equality) and no additional regularization is enforced on the OT plan. In this context, we show that the corresponding optimization problem can be reformulated as a non-negative penalized linear regression problem. This reformulation allows us to propose novel algorithms inspired from inverse problems and nonnegative matrix factorization. In particular, we consider majorization-minimization which leads in our setting to efficient multiplicative updates for a variety of penalties. Furthermore, we derive for the first time an efficient algorithm to compute the regularization path of UOT with quadratic penalties. The proposed algorithm provides a continuity of piece-wise linear OT plans converging to the solution of balanced OT (corresponding to infinite penalty weights). We perform several numerical experiments on simulated and real data illustrating the new algorithms, and provide a detailed discussion about more sophisticated optimization tools that can further be used to solve OT problems thanks to our reformulation.

Keywords

Cite

@article{arxiv.2106.04145,
  title  = {Unbalanced Optimal Transport through Non-negative Penalized Linear Regression},
  author = {Laetitia Chapel and Rémi Flamary and Haoran Wu and Cédric Févotte and Gilles Gasso},
  journal= {arXiv preprint arXiv:2106.04145},
  year   = {2021}
}

Comments

Laetitia Chapel and R\'emi Flamary have equal contribution

R2 v1 2026-06-24T02:56:47.183Z