AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Online Adaptive Methods, Universality and Acceleration

Kfir Y. Levy, Alp Yurtsever, Volkan Cevher

NeurIPS 2018 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 25 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
Use AcceleGrad instead of AdaGraddeterministic regression optimization · Synthetic smooth and non-smooth regressionconvergenceImproved
Use AcceleGrad instead of universal line-search methodsstochastic regression optimization · Synthetic regression with minibatch noisy gradientsconvergenceImproved
Increase minibatch sizeAcceleGrad · Real-dataset large-minibatch experimentsperformance per gradient calculationImproved
Increase minibatch sizeAdaGrad · Real-dataset large-minibatch experimentsperformanceHurt
Use a smaller line-search parameter εuniversal gradient methods · Smooth regressionconvergenceImproved
Use a smaller line-search parameter εuniversal gradient methods · Non-smooth regressionconvergenceHurt
Use a larger line-search parameter εuniversal gradient methods · Non-smooth regressionconvergenceHurt
Use AcceleGrad's final iterates instead of its weighted averageAcceleGrad · Offline optimization experimentsconvergenceImproved
Use universal line-search methods with noisy gradientsuniversal gradient methods · Stochastic regression optimizationconvergenceHurt

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