AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Alternating Minimizations Converge to Second-Order Optimal Solutions

Qiuwei Li, Zhihui Zhu, Gongguo Tang

ICML 2019 · Optimization › Nonconvex and smooth optimization · approach: Nonconvex minimax and constrained methods · 37 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
Add a strong bi-convexity condition plus full-row-rank cross Hessian at strict saddles to alternating minimization (Algorithm 1)standard alternating minimization · theoretical analysis (strict saddle avoidance)convergence to strict saddles from random initializationImproved
Use proximal alternating minimization with proximal parameter beta > Lf under bi-smoothnessproximal alternating minimization (Algorithm 2) · theoretical analysis (strict saddle avoidance)convergence to strict saddles from random initializationImproved
Restrict to a non-singular Jacobian at strict saddles (full-rank cross Hessian) for alternating minimizationstandard alternating minimization · best rank-1 matrix PCA examplesecond-order convergence guaranteeNo 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