Claudia Merger — accepted AI-conference papers

2026

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights

Fabiola Ricci, Claudia Merger, Sebastian Goldt

ICML 2026poster

Neural networks trained with gradient-based methods exhibit a strong simplicity bias, learning simpler statistical features of their data before moving to more complex features. In this work, we study this bias from a Fourier perspective, motivated by the approximate translation-invariance and the c…

Cited by 0 Source ↗Scholar ↗

2026

A theory of learning data statistics in diffusion models, from easy to hard

Lorenzo Bardone, Claudia Merger, Sebastian Goldt

ICML 2026poster

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 that standard diffusion models trained on natural images exhibit a simplicity bias, learning simple, pair-wise input stat…

Cited by 0 Source ↗Scholar ↗