Sketching meets random projection in the dual: a provable recovery algorithm for big and high-dimensional data

DOI10.1214/17-EJS1334SIzbMath1470.62068arXiv1610.03045OpenAlexW2773306503MaRDI QIDQ1688973

Jialei Wang, Nathan Srebro, Mehrdad Mahdavi, Mladen Kolar, Jason D. Lee

Publication date: 12 January 2018

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1610.03045

zbMATH Keywords

preconditioningaccelerationconjugate gradientdual random projectioniterative Hessian sketchprimal-dual conversionprimal-dual sketch

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Large-scale problems in mathematical programming (90C06) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (12)

An asymptotic analysis of distributed nonparametric methods ⋮ Convexification with Bounded Gap for Randomly Projected Quadratic Optimization ⋮ M-IHS: an accelerated randomized preconditioning method avoiding costly matrix decompositions ⋮ Adaptive iterative Hessian sketch via \(A\)-optimal subsampling ⋮ Random projections of linear and semidefinite problems with linear inequalities ⋮ Regularized Linear Inversion with Randomized Singular Value Decomposition ⋮ An investigation of Newton-Sketch and subsampled Newton methods ⋮ Randomized sketches for kernel CCA ⋮ Unnamed Item ⋮ Approximate nonparametric quantile regression in reproducing kernel Hilbert spaces via random projection ⋮ On nonparametric randomized sketches for kernels with further smoothness ⋮ ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching

This page was built for publication: Sketching meets random projection in the dual: a provable recovery algorithm for big and high-dimensional data