Statistical and Computational Guarantees for Influence Diagnostics
From MaRDI portal
Publication:6419926
arXiv2212.04014MaRDI QIDQ6419926
Author name not available (Why is that?)
Publication date: 7 December 2022
Abstract: Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as computational complexity bounds, for influence functions and approximate maximum influence perturbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.
Has companion code repository: https://github.com/jfisher52/influence_theory
This page was built for publication: Statistical and Computational Guarantees for Influence Diagnostics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6419926)
