How Much Does Your Data Exploration Overfit? Controlling Bias via Information Usage

DOI10.1109/TIT.2019.2945779zbMath1433.94041arXiv1511.05219OpenAlexW2979452771MaRDI QIDQ5211602

Daniel J. Russo, James Zou

Publication date: 28 January 2020

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1511.05219

Mathematics Subject Classification ID

Informational aspects of data analysis and big data (94A16) Statistical aspects of big data and data science (62R07)

Related Items (6)

Unnamed Item ⋮ Smoothed noise contrastive mutual information neural estimation ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ The role of mutual information in variational classifiers ⋮ A Finite Time Analysis of Temporal Difference Learning with Linear Function Approximation ⋮ Hausdorff dimension, heavy tails, and generalization in neural networks*

This page was built for publication: How Much Does Your Data Exploration Overfit? Controlling Bias via Information Usage