2 layer neural networks as Wasserstein gradient flows

From Optimal Transport Wiki
Revision as of 01:16, 10 February 2022 by Paigehillen (talk | contribs) (Created page with "The Monge Problem <ref name="Figalli" /> is a problem in [http://34.106.105.83/wiki/Main_Page Optimal Transport] concerning the best way to rearrange mass. It was the earliest...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

The Monge Problem [1] is a problem in Optimal Transport concerning the best way to rearrange mass. It was the earliest formulation of a problem in Optimal Transport and was later generalized to the Kantorovich Problem. Unlike the Kantorovich Problem, which allows the splitting of mass, the Monge Problem asks for the most efficient allocation map that doesn't assign any mass from any source to more than one location.

Motivation

Shallow Neural Networks

Continuous Formulation

Minimization Problem

Wasserstein Gradient Flow

Main Results

References

  1. [https://people.math.ethz.ch/~afigalli/lecture-notes-pdf/The-continuous-formulation-of-shallow-neural-networks-as-wasserstein-type-gradient-flows.pdf XAVIER FERNANDEZ-REAL AND ALESSIO FIGALLI, THE CONTINUOUS FORMULATION OF SHALLOW NEURAL NETWORKS AS WASSERSTEIN-TYPE GRADIENT FLOWS]