Pith. sign in

Lotka-Volterra Model with Mutations and Generative Adversarial Networks

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

A model of population genetics of the Lotka-Volterra type with mutations on a statistical manifold is introduced. Mutations in the model are described by diffusion on a statistical manifold with a generator in the form of a Laplace-Beltrami operator with a Fisher-Rao metric, that is, the model combines population genetics and information geometry. This model describes a generalization of the model of machine learning theory, the model of generative adversarial network (GAN), to the case of populations of generative adversarial networks. The introduced model describes the control of overfitting for generative adversarial networks.

citation-role summary

extension 1

citation-polarity summary

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

roles

extension 1

polarities

extend 1

representative citing papers

Control of Overfitting with Physics

cs.LG · 2024-12-14 · conditional · novelty 5.0

SGLD favors wide loss minima through the Eyring free-energy formula, and GANs act like a predator-prey system that pushes learning out of narrow likelihood maxima.

citing papers explorer

Showing 1 of 1 citing paper.

  • Control of Overfitting with Physics cs.LG · 2024-12-14 · conditional · none · ref 8 · internal anchor

    SGLD favors wide loss minima through the Eyring free-energy formula, and GANs act like a predator-prey system that pushes learning out of narrow likelihood maxima.