Thesis etd-08232022-160426 |
Link copiato negli appunti
Thesis type
Tesi di laurea magistrale
URN
etd-08232022-160426
Thesis title
A study on the connection between Mean Field Games and Generative Adversarial Network
Department
MATEMATICA
Course of study
MATEMATICA
Supervisors
.
relatore Prof.ssa Livieri, Giulia
Keywords
- generative adversarial networks
- mean field games
Graduation session start date
23/09/2022
Availability
None
Abstract (Inglese)
Abstract (Italiano)
We analyse the connection between Mean Field Games (MFGs) and a popular Machine Learning model, namely Generative Adversarial Networks (GANs). From the game theoretical perspective, GANs can be interpreted as MFGs under Pareto Optimality condition. On the other side, we take advantage of the adversarial nature of GANs in order to numerically approximate Mean Field Equilibria, which are expressed as solutions of a system of coupled PDEs: a forward Fokker-Plank equation and a backward Hamilton-Jacobi-Bellman equation.
File
| Nome file | Dimensione |
|---|---|
Thesis not available for consultation. |
|