AI RESEARCH

Compositional Sparsity as an Inductive Bias for Neural Architecture Design

arXiv CS.LG

ArXi:2605.14764v1 Announce Type: new Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning is driven by compositional sparsity, where target functions decompose into constituents ed on low-dimensional variable subsets.