Understanding deep learning is increasingly emergent as it penetrates more and more into
industry and science. In recent years, a research line from Fourier analysis sheds light on …

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-
trained models directly in weight space: By adding the fine-tuned weights of different tasks …

Implicit neural representations (INRs) have recently emerged as a promising alternative to
classical discretized representations of signals. Nevertheless, despite their practical …

Modern deep neural networks are highly over-parameterized compared to the data on which
they are trained, yet they often generalize remarkably well. A flurry of recent work has asked …

Neural networks in the lazy training regime converge to kernel machines. Can neural
networks in the rich feature learning regime learn a kernel machine with a data-dependent …

The adversarial vulnerability of neural nets, and subsequent techniques to create robust
models have attracted significant attention; yet we still lack a full understanding of this …

For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully
characterizes generalization, but for the networks used in practice, the empirical NTK only …

It is unclear how changing the learning rule of a deep neural network alters its learning
dynamics and representations. To gain insight into the relationship between learned …

We investigate the spectral properties of linear-width feed-forward neural networks, where
the sample size is asymptotically proportional to network width. Empirically, we show that the …

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures
the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) …