How to Inverting the Leverage Score Distribution?

arXiv:2404.13785v1 Announce Type: new
Abstract: Leverage score is a fundamental problem in machine learning and theoretical computer science. It has extensive applications in regression analysis, randomized algorithms, and neural network inversion. Despite leverage scores are widely used as a tool, in this paper, we study a novel problem, namely the inverting leverage score problem. We analyze to invert the leverage score distributions back to recover model parameters. Specifically, given a leverage score $\sigma \in \mathbb{R}^n$, the matrix $A \in \mathbb{R}^{n …

abstract algorithms analysis applications arxiv computer computer science cs.lg distribution fundamental machine machine learning network neural network novel paper regression science study tool type