Unbalanced Optimal Transport through Non-negative Penalized Linear Regression
arXiv:2106.04145
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.
arXiv commentLaetitia Chapel and Rémi Flamary have equal contribution
References in corpus (19)
- Scikit-learn: Machine Learning in Python
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Rejoinder to "Least angle regression" by Efron et al
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Learning with a Wasserstein Loss
- Optimal Transport for structured data with application on graphs
- Safe Feature Elimination for the LASSO and Sparse Supervised Learning Problems
- Smooth and Sparse Optimal Transport
- A Fast Proximal Point Method for Computing Exact Wasserstein Distance
- Sinkhorn Divergences for Unbalanced Optimal Transport
- Outlier-Robust Optimal Transport