Balancing Statistical and Computational Precision: A General Theory and Applications to Sparse Regression

DOI10.1109/TIT.2022.3203857arXiv1609.07195OpenAlexW4294312833MaRDI QIDQ6196108

M. Taheri, Johannes Lederer, Néhémy Lim

Publication date: 14 March 2024

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

Abstract: Modern technologies are generating ever-increasing amounts of data. Making use of these data requires methods that are both statistically sound and computationally efficient. Typically, the statistical and computational aspects are treated separately. In this paper, we propose an approach to entangle these two aspects in the context of regularized estimation. Applying our approach to sparse and group-sparse regression, we show that it can improve on standard pipelines both statistically and computationally.

Full work available at URL: https://arxiv.org/abs/1609.07195

zbMATH Keywords

oracle inequalitieshigh-dimensional regressiongroup-feature selection

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Statistical aspects of big data and data science (62R07)

Related Items (1)

Layer sparsity in neural networks

This page was built for publication: Balancing Statistical and Computational Precision: A General Theory and Applications to Sparse Regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6196108)