Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension

ArXi:2510.01105v2 Announce Type: replace Neural multivariate regression underpins a wide range of domains, including control, robotics, and finance, yet the geometry of its learned representations remains poorly characterized. While neural collapse has been shown to benefit generalization in classification, we find that analogous collapse in regression consistently degrades performance. To explain this contrast, we analyze regression models through the lens of intrinsic dimension.