Optimal Transport for Generative Models

Xianfeng Gu (), Na Lei () and Shing-Tung Yau ()
Additional contact information
Xianfeng Gu: Stony Brook University, Stony Brook
Na Lei: Dalian University of Technology
Shing-Tung Yau: Harvard University

Chapter 47 in Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging, 2023, pp 1659-1706 from Springer

Abstract: Abstract Optimal transport plays a fundamental role in deep learning. Natural data sets have intrinsic patterns, which can be summarized as the manifold distribution principle: a natural class of data can be treated as a probability distribution on a low-dimensional manifold, embedded in a high-dimensional ambient space. A deep learning system mainly accomplishes two tasks: manifold learning and probability distribution learning. Given a manifold X, all the probability measures on X form an infinite dimensional manifold, the so-called Wasserstein space. Optimal transport assigns a Riemannian metric on the Wasserstein space, the so-called Wasserstein metric, and defines Otto’s calculus, such that variational optimization can be carried out in the Wasserstein space P ( X ) $$\mathcal {P}(X)$$ . A deep learning system learns the distribution by optimizing some functionals in the Wasserstein space P ( X ) $$\mathcal {P}(X)$$ ; therefore optimal transport lays down the theoretic foundation for deep learning. This work introduces the theory of optimal transport and the profound relation between Brenier’s theorem and Alexandrov’s theorem in differential geometry via Monge-Ampère equation. We give a variational proof for Alexandrov’s theorem and convert the proof to a computational algorithm to solve the optimal transport maps. The algorithm is based on computational geometry and can be generalized to general manifold setting. Optimal transport theory and algorithms have been extensively applied in the models of generative adversarial networks (GANs). In a GAN model, the generator computes the optimal transport map (OT map), while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution. The optimal transport theory shows the competition between the generator and the discriminator is completely unnecessary and should be replaced by collaboration. Furthermore, the regularity theory of optimal transport map explains the intrinsic reason for mode collapsing. A novel generative model is introduced, which uses an autoencoder (AE) for manifold learning and OT map for probability distribution transformation. This AE-OT model improves the theoretical rigor and transparency, as well as the computational stability and efficiency; in particular, it eliminates the mode collapsing.

Keywords: Explainable deep learning; Optimal Transport; Convex Geometry; Generative adversarial networks; Manifold learning; Monge-Ampère Equation (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-98661-2_105

Ordering information: This item can be ordered from
http://www.springer.com/9783030986612

DOI: 10.1007/978-3-030-98661-2_105

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().