26–30 Jun 2023
ECT*
Europe/Rome timezone

$λφ^4$ Scalar Neural Network Field Theory

30 Jun 2023, 10:00
25m
Aula Renzo Leonardi (ECT*)

Aula Renzo Leonardi

ECT*

Strada delle Tabarelle 286, I-38123 Villazzano (Trento)

Speakers

Anindita Maiti (Harvard University)Dr Anindita Maiti (Harvard University)

Description

Neural Network (NN) architectures at initialization define field theories. Certain large width limits of architectures result in free field theories due to Central Limit Theorem (CLT); deviations from CLT via finite width, and correlated, dissimilar NN parameters turn on field interactions. Edgeworth method provides a way to construct NN field theory actions using connected Feynman diagrams, where internal vertices correspond to connected correlators of NN field theories. Further, specific interacting field theories can be engineered via the NN parameter framework, where non-Gaussianities due to statistical independence breaking of NN parameters tune the action deformations. As an example, I will present the construction of $λφ^4$ scalar field theory in infinite width NNs.

Primary authors

Dr Anindita Maiti (Harvard University) Prof. James Halverson (Northeastern University) Prof. Matthew D. Schwartz Dr Mehmet Demirtas (Northeastern University)

Presentation materials