Diffusion Probabilistic Models (DPMs) have achieved considerable success...
The diffusion probabilistic generative models are widely used to generat...
Recently, generalization on out-of-distribution (OOD) data with correlat...
In real-world applications, it is important and desirable to learn a mod...
It is arguably believed that flatter minima can generalize better. Howev...
Batch normalization (BN) has become a crucial component across diverse d...
In this paper, we provide a unified analysis of the excess risk of the m...
It was empirically confirmed by Keskar et al.SharpMinima that flatter
mi...