EW2JR5aVLm@OpenReview

Total: 1

#1 Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes [PDF1] [Copy] [Kimi1] [REL]

Authors: Dongjae Jeon, Dueun Kim, Albert No

In this paper, we introduce a geometric framework to analyze memorization in diffusion models through the sharpness of the log probability density. We mathematically justify a previously proposed score-difference-based memorization metric by demonstrating its effectiveness in quantifying sharpness. Additionally, we propose a novel memorization metric that captures sharpness at the initial stage of image generation in latent diffusion models, offering early insights into potential memorization. Leveraging this metric, we develop a mitigation strategy that optimizes the initial noise of the generation process using a sharpness-aware regularization term.

Subject: ICML.2025 - Spotlight