AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation

NeurIPS 2018 · Optimization › Nonconvex and smooth optimization · approach: Langevin sampling for nonconvex problems · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 Gen-Oja instead of alternating Oja + tau steps of averaged SGD (tau=10, 1000, 10000)Gen-Oja · Synthetic generalized eigenvalue problem (d=20, T=10^6)log10 sin_B errorHelped
vary inner SGD steps tau in two-step baseline (10 vs 1000 vs 10000) (ablation)two-step Oja+SGD baseline · Synthetic generalized eigenvalue problemlog10 sin_B errorMixed
scale step size alpha by 1, 1/8, 1/16 of alpha*=1/R^2 (ablation)Gen-Oja · Synthetic generalized eigenvalue problemlog10 sin_B errorNo clear effect
shrink constant in beta_t = beta*/t by 16x (ablation)Gen-Oja · Synthetic generalized eigenvalue problemlog10 sin_B errorHurt
add streaming averaging with beta_t proportional to 1/sqrt(t) (ablation)Gen-Oja · Synthetic generalized eigenvalue problemlog10 sin_B errorHelped

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