paper-with-me

홈 › Papers

Understanding Memorization in Generative Models via Sharpness in Probability Landscapes

2024-12-05 · Dongjae Jeon, Dueun Kim, Albert No

In this paper, we introduce a geometric framework to analyze memorization in diffusion models using the eigenvalues of the Hessian of the log probability density. We propose that memorization arises from isolated points in the learned probability distribution, characterized by sharpness in the probability landscape, as indicated by large negative eigenvalues of the Hessian. Through experiments on various datasets, we demonstrate that these eigenvalues effectively detect and quantify memorization. Our approach provides a clear understanding of memorization in diffusion models and lays the groundwork for developing strategies to ensure secure and reliable generative models

📄 PDF Abstract BibTeX arXiv:2412.04140

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Latent Geometry and Memorization in Generative Models

2017-05-25 · Matt Feiszli

It can be difficult to tell whether a trained generative model has learned to generate novel examples or has simply memorized a specific set of outputs. In published work, it is common to attempt to address this visually…

Memorization

On Memorization and Privacy Risks of Sharpness Aware Minimization

2023-09-30 · Young In Kim, Pratiksha Agrawal, Johannes O. Royset, Rajiv Khanna

In many recent works, there is an increased focus on designing algorithms that seek flatter optima for neural network loss optimization as there is empirical evidence that it leads to better generalization performance in…

Memorization

Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes

2024-12-18 · CVPR 2025 1 · Aodi Li, Liansheng Zhuang, Xiao Long, Minghong Yao 외

Domain generalization aims to learn a model from multiple training domains and generalize it to unseen test domains. Recent theory has shown that seeking the deep models, whose parameters lie in the flat minima of the lo…

Domain Generalization

Memorization in 3D Shape Generation: An Empirical Study

2025-12-29 · Shu Pu, Boya Zeng, Kaichen Zhou, Mengyu Wang 외 arxiv

Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent t…

On Memorization in Probabilistic Deep Generative Models

2021-06-06 · Gerrit J. J. van den Burg, Christopher K. I. Williams

Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been …

Density EstimationMemorization