Abstract
Correctly estimating the discrepancy between two data distributions has always been an important task in Machine Learning. Recently, Cuturi proposed the Sinkhorn distance [1] which makes use of an approximate Optimal Transport cost between two distributions as a distance to describe distribution discrepancy. Although it has been successfully adopted in various machine learning applications (e.g. in Natural Language Processing and Computer Vision) since then, the Sinkhorn distance also suffers from two unnegligible limitations. The first one is that the Sinkhorn distance only gives an approximation of the real Wasserstein distance, the second one is the ‘divide by zero’ problem which often occurs during matrix scaling when setting the entropy regularization coefficient to a small value. In this paper, we introduce a new Brenier approach for calculating a more accurate Wasserstein distance between two discrete distributions, this approach successfully avoids the two limitations shown above for Sinkhorn distance and gives an alternative way for estimating distribution discrepancy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Here \(\mathbf {1}_d\) is a d-dimensional column vector of ones.
References
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, pp. 2292–2300 (2013)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(Mar), 723–773 (2012)
Gu, X., Luo, F., Sun, J., Yau, S.-T.: Variational principles for Minkowski type problems, discrete optimal transport, and discrete Monge-Ampere equations. arXiv preprint arXiv:1302.5472 (2013)
Villani, C.: Optimal Transport: Old and New, vol. 338. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-71050-9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, Y., Chen, L., Saidi, A., Gu, X. (2019). Brenier Approach for Optimal Transportation Between a Quasi-discrete Measure and a Discrete Measure. In: Chen, L., Ben Amor, B., Ghorbel, F. (eds) Representations, Analysis and Recognition of Shape and Motion from Imaging Data. RFMI 2017. Communications in Computer and Information Science, vol 842. Springer, Cham. https://doi.org/10.1007/978-3-030-19816-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-19816-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19815-2
Online ISBN: 978-3-030-19816-9
eBook Packages: Computer ScienceComputer Science (R0)