Year: 2025
Type: preprint
Abstract: Despite the remarkable performance of generative Diffusion Models (DMs), their internal working is still not well understood, which is potentially problematic. This paper focuses on exploring the important notion of bias-variance tradeoff in diffusion models. Providing a systematic foundation for this exploration, it establishes that at one extreme, the diffusion models may amplify the inherent bias in the training data, and on the other, they may compromise the presumed privacy of the training samples. Our exploration aligns with the memorization-generalization understanding of the generative models, but it also expands further along this spectrum beyond "generalization", revealing the risk of bias amplification in deeper models. Our claims are validated both theoretically and empirically.
Source: arXiv (Cornell University)
Authors: Hakemi, Shahin, Akhtar, Naveed, Hassan, Ghulam Mubashar, Mian, Ajmal
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6967246265
Cites:
Cited by:
Related to: