Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation

Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation










arXiv:2511.09002v1 Announce Type: new
Abstract: Self-consuming generative models have received significant attention over the last few years. In this paper, we study a self-consuming generative model with heterogeneous preferences that is a generalization of the model in Ferbach et al. (2024). The model is retrained round by round using real data and its previous-round synthetic outputs. The asymptotic behavior of the retraining dynamics is investigated across four regimes using different techniques including the nonlinear Perron–Frobenius theory. Our analyses improve upon that of Ferbach et al. (2024) and provide convergence results in settings where the well-known Banach contraction mapping arguments do not apply. Stability and non-stability results regarding the retraining dynamics are also given.






Hongru Zhao, Jinwen Fu, Tuan Pham





Go to original source





Posted

in

, ,

by