[Paper Reading]: Why Diffusion Models Don't Memorize

This week, we will walk through and discuss the paper: Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training [https://arxiv.org/pdf/2505.17638]

Abstract of the paper:
Diffusion models have achieved remarkable success across a wide range of generative tasks. A key challenge is understanding the mechanisms that prevent their memorization of training data and allow generalization. In this work, we investigate the role of the training dynamics in the transition from generalization to memorization. Through extensive experiments and theoretical analysis, we identify two distinct timescales: an early time \tau_\mathrm{gen} at which models begin to generate high-quality samples, and a later time \tau_\mathrm{mem} beyond which memorization emerges. Crucially, we find that \tau_\mathrm{mem} increases linearly with the training set size n, while \tau_\mathrm{gen} remains constant. This creates a growing window of training times with n where models generalize effectively, despite showing strong memorization if training continues beyond it. It is only when n becomes larger than a model-dependent threshold that overfitting disappears at infinite training times. These findings reveal a form of implicit dynamical regularization in the training dynamics, which allow to avoid memorization even in highly overparameterized settings. Our results are supported by numerical experiments with standard U-Net architectures on realistic and synthetic datasets, and by a theoretical analysis using a tractable random features model studied in the high-dimensional limit.

-----------------

We are a group of applied AI practitioners and enthusiasts who have formed a collective learning community. Every Wednesday evening at PM PST, we hold our research paper reading seminar covering an AI topic. One member carefully explains the paper, making it more accessible to a broader audience. Then, we follow this reading with a more informal discussion and socializing.
You are welcome to join this in person or over Zoom. SupportVectors is an AI training lab located in Fremont, CA, close to Tesla and easily accessible by road and BART. We follow the weekly sessions with snacks, soft drinks, and informal discussions.
If you want to attend by Zoom, the Zoom registration link will be visible once you RSVP. Note that we have had to change and add security to the Zoom link to prevent Zoom bombing.