From Optimal Control to Mean Field Optimal Transport via Stochastic Neural Networks-Reference-Cited by-同舟云学术

From Optimal Control to Mean Field Optimal Transport via Stochastic Neural Networks

Published:2023-09-08 Issue:9 Volume:15 Page:1724
ISSN:2073-8994
Container-title:Symmetry
language:en
Short-container-title:Symmetry

Author:

Di Persio Luca¹^ORCID,Garbelli Matteo¹²^ORCID

Affiliation:

1. Department of Computer Science, University of Verona, Strada le Grazie 15, 37134 Verona, Italy

2. Department of Mathematics, University of Trento, Via Sommarive 14, Povo, 38123 Trento, Italy

Abstract

In this paper, we derive a unified perspective for Optimal Transport (OT) and Mean Field Control (MFC) theories to analyse the learning process for Neural Network algorithms in a high-dimensional framework. We consider a Mean Field Neural Network in the context of MFC theory referring to the mean field formulation of OT theory that may allow the development of efficient algorithms in a high-dimensional framework while providing a powerful tool in the context of explainable Artificial Intelligence.

Publisher

MDPI AG

Subject

Physics and Astronomy (miscellaneous),General Mathematics,Chemistry (miscellaneous),Computer Science (miscellaneous)

Link

https://www.mdpi.com/2073-8994/15/9/1724/pdf

Reference30 articles.

1. A measure theoretical approach to the mean-field maximum principle for training NeurODEs;Bonnet;Nonlinear Anal.,2023

2. A mean-field optimal control formulation of deep learning;E;Res. Math. Sci.,2019

3. A backward SDE method for uncertainty quantification in deep learning;Archibald;Discret. Contin. Dyn. Syst.,2022

4. de Bie, G., Peyré, G., and Cuturi, M. (2019, January 9–15). Stochastic Deep Networks. Proceedings of the 36th International Conference on Machine Learning, PMLR 97, Long Beach, CA, USA.

5. Baudelet, S., Frénais, B., Laurière, M., Machtalay, A., and Zhu, Y. (2023). Deep Learning for Mean Field Optimal Transport. arXiv.