Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908650011885568 |
|---|---|
| author | Zhao, Hongru Fu, Jinwen Pham, Tuan |
| author_facet | Zhao, Hongru Fu, Jinwen Pham, Tuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09002 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation Zhao, Hongru Fu, Jinwen Pham, Tuan Machine Learning 37N40 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. |
| title | Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation |
| topic | Machine Learning 37N40 |
| url | https://arxiv.org/abs/2511.09002 |