AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Scalable Approximations for Generalized Linear Problems

Murat Erdogdu, Mohsen Bayati, Lee H. Dicker

JMLR 2019 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis

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 SLS (OLS then scaling) instead of Newton-Raphson MLElogistic regression, random init · Logistic synthetictime to min test error (s): 301.06 -> 8.34Improved
use SLS instead of gradient descentHiggs logistic, random init · Higgstime to min test error (s): 100871 -> 13.18Improved
use SLS instead of Newton-RaphsonCovertype Poisson, random init · Covertypetime to min test error (s): 16.7 -> 2.71Improved
use SLS instead of BFGSCovertype Poisson, random init · Covertypetime to min test error (s): 5.12 -> 2.71Improved
use SLS instead of Newton-SteinCovertype Poisson, OLS init · Covertypetime to min test error (s): 282.1 -> 1.66Improved
initialize SLS with OLS instead of random start (ablation)SLS, logistic synthetic · Logistic synthetictime to min test error (s): 8.34 -> 2.94Improved
initialize Newton-Raphson with OLS instead of random start (ablation)Newton-Raphson, logistic synthetic · Logistic synthetictime to min test error (s): 301.06 -> 82.57Improved
initialize Newton-Raphson with OLS instead of random start (ablation)Newton-Raphson, Covertype Poisson · Covertypetime to min test error (s): 16.7 -> 32.48Hurt
initialize Newton-Stein with OLS instead of random start (ablation)Newton-Stein, Covertype Poisson · Covertypetime to min test error (s): 21.17 -> 282.1Hurt
initialize SLS with OLS instead of random start (ablation)SLS, Covertype Poisson · Covertypetime to min test error (s): 2.71 -> 1.66Improved
use SLS instead of exact MLEHiggs logistic · Higgstest error: 22.40% vs 22.38%No 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