Showing 2026Show all
3 papers · 1 filter
cond-mat.dis-nn2026
Local Coverage Governs Memorization in Diffusion Models
Claudia Merger, Sebastian Goldt
Memorization in diffusion models is often treated as a global property of the model or dataset. In practice, however, a single diffusion model can simultaneously generate both memo…
stat.ML2026
A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
Fabiola Ricci, Claudia Merger, Sebastian Goldt
Neural networks trained with gradient-based methods exhibit a strong simplicity bias: they learn simpler statistical features of their data before moving to more complex features.…
stat.ML2026
A theory of learning data statistics in diffusion models, from easy to hard
Lorenzo Bardone, Claudia Merger, Sebastian Goldt
While diffusion models have emerged as a powerful class of generative models, their learning dynamics remain poorly understood. We address this issue first by empirically showing t…