AI Paper Atlas

Research map / Optimization / Optimizers

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures

Zhaozhuo Xu, Zhao Song, Anshumali Shrivastava

NeurIPS 2021 · Optimization › Optimizers · approach: Randomized gradient estimation · 3 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
replace exact greedy direction search with LSH-based approximate MaxIP in Frank-WolfeFrank-Wolfe · complexity analysiscost per iterationImproved
replace exact search with LSH MaxIP in kernel herdingHerding · complexity analysiscost per iterationImproved
replace exact search with LSH MaxIP in projection-free policy gradientPolicy gradient · complexity analysiscost per iterationImproved

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