AI RESEARCH
Learning with Shallow Neural Networks on Cluster-Structured Features
arXiv CS.LG
•
ArXi:2605.14927v1 Announce Type: new The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While standard theoretical models typically assume that this structure lies in the target function, projecting unstructured inputs onto a low-dimensional subspace, data such as images, text or genomic sequences exhibit strong spatial correlations within the input space itself.