AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Iterative Hessian Sketch: Fast and Accurate Solution Approximation for Constrained Least-Squares

Mert Pilanci, Martin J. Wainwright

JMLR 2016 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized sketching for matrices · 146 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use IHS (sketched subproblems) instead of homotopy on the original problem, with sketching time includedLasso via homotopy · Sparse regression running time, n=524288, d=500running time (seconds): 12.0969 -> 5.5792Improved
use IHS without sketching time instead of homotopy on the original problemLasso via homotopy · Sparse regression running time, n=524288, d=500running time (seconds): 12.0969 -> 3.1593Improved
use IHS on the smallest problem including sketching timeLasso via homotopy · Sparse regression running time, n=4096, d=500running time (seconds): 0.0840 -> 0.0877Hurt
use IHS instead of naive sketch with same total number of projectionsl1-constrained least squares · Sparse least squares, d in {16..256}error: 0.11 vs roughly twice as large for the naive sketchImproved
use IHS instead of classical sketch for nuclear-norm constrained matrix regression over nnuclear-norm least squares · Matrix recovery 20x20, Figure 8amean-squared errorImproved
use IHS instead of classical sketch for multi-task classifier on JAFFEnuclear-norm multi-task classifier · JAFFE facial expressionclassification error rateImproved
use IHS sketched solution instead of original least-squares solution for predictionsparse least squares · Prediction MSE versus n, Figure 6prediction MSENo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy