Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Self-Consuming Generative Models with Adversarially Curated Data
Recent advances in generative models have made it increasingly difficult to distinguish real data from model-generated synthetic data. Using synthetic data for successive training of future model generations creates "sel…
Self-Correcting Self-Consuming Loops for Generative Model Training
As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite the successful stories of using synthetic…
Motion SynthesisRepresentation LearningStabilizing Consistency Training: A Flow Map Analysis and Self-Distillation
Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when train…
Image GenerationSelf-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
The rapid progress in generative models has resulted in impressive leaps in generation quality, blurring the lines between synthetic and real data. Web-scale datasets are now prone to the inevitable contamination by synt…
Training in reverse: How iteration order influences convergence and stability in deep learning
Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issue…