AI RESEARCH
Information Hidden in Gradients of Regression with Target Noise
arXiv CS.LG
•
ArXi:2601.18546v2 Announce Type: replace Second-order information -- such as curvature or data covariance -- is critical for optimisation, diagnostics, and robustness. However, in many modern settings, only the gradients are observable. We show that the gradients alone can reveal the Hessian, equalling the data covariance $\Sigma$ for the linear regression.