Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds

DOI10.1109/TIT.2022.3146206zbMath1497.62152arXiv2012.07054OpenAlexW4226197126MaRDI QIDQ5088469

Jonathan Lacotte, Mert Pilanci

Publication date: 13 July 2022

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

Full work available at URL: https://arxiv.org/abs/2012.07054

zbMATH Keywords

approximation properties via convex duality and Fenchel conjugateshigh-dimensional convex problemsoblivious and data-adaptive subspacesrandomized optimization methods

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Convex programming (90C25) Numerical optimization and variational techniques (65K10)

Related Items (5)

Towards Practical Large-Scale Randomized Iterative Least Squares Solvers through Uncertainty Quantification ⋮ Local laws for multiplication of random matrices ⋮ Randomized Nyström Preconditioning ⋮ Spiked multiplicative random matrices and principal components ⋮ Unnamed Item

This page was built for publication: Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds