AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Heavy Ball Momentum for Conditional Gradient

Bingcong Li, Alireza Sadeghi, Georgios B. Giannakis

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Stochastic Frank-Wolfe methods · 2 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 heavy-ball momentum with δ_k = η_k = 2/(k+2)Frank-Wolfe · Convex smooth optimizationprimal-dual error bound: 4LD^2/(k+1) -> 2LD^2/(k+1)Improved
Add restart when the standard FW gap is smaller than the generalized gapHFW · Convex smooth optimizationprimal-dual error bound: 2LD^2/(k+1) -> 2LD^2/(k + C^s)Improved
Use uniform averaging of past gradients, δ_k = 1/(k+1), instead of the 2/(k+2) schedule (ablation)HFW · Convex smooth optimizationprimal-dual error bound: 2LD^2/(k+1) -> LD^2 ln (k+1)/(2k)Hurt
Use a directional local Lipschitz constant instead of the global constant (ablation)HFW smooth step size · Binary classification datasetsconvergence speed: by an order of magnitudeImproved
Use WFW rather than UFW (ablation)HFW · Binary classification, ℓ2-, ℓ1-, and n-support norm ballsprimal error convergenceImproved
Use UFW rather than FW (ablation)HFW · Binary classification, ℓ2-norm ballprimal error convergenceMixed
Use UFW rather than FW (ablation)HFW · Binary classification, n-support norm ballprimal error convergenceNo clear effect
Use UFW-s rather than WFW-s (ablation)HFW with smooth step sizes · Binary classification, n-support norm ballprimal error convergenceHurt
Use directional smooth step sizes with UFW instead of WFW (ablation)HFW · Binary classification datasetsprimal error convergenceHurt
Add restart (ablation)WFW · Binary classificationprimal error convergenceImproved
Use WFW rather than FW (ablation)Frank-Wolfe · MovieLens100K matrix completionoptimality errorImproved
Use UFW-s rather than WFW-s (ablation)HFW with smooth step sizes · MovieLens100K matrix completionsolution rankImproved

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