AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Stagewise Training Accelerates Convergence of Testing Error Over SGD

Zhuoning Yuan, Yan Yan, Rong Jin, Tianbao Yang

NeurIPS 2019 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 12 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 stagewise training instead of SGD with a polynomially decaying step sizeStagewise training on CIFAR-10 and CIFAR-100 with ResNets and ConvNets · CIFAR-10 and CIFAR-100testing errorImproved
Use stagewise training instead of SGD with a polynomially decaying step sizeStagewise training with convex losses · real-sim and E2006-tfidftesting errorImproved
Add explicit regularization at each stage (ablation)Stagewise SGD (V1) · CIFAR-10 and CIFAR-100generalization errorImproved
Add explicit regularization at each stage (ablation)Stagewise SGD (V1) · CIFAR-10 and CIFAR-100training errorHurt
Return the averaged solution at each stage instead of the last solution (ablation)Stagewise SGD (V2) · CIFAR-10 and CIFAR-100generalization errorImproved
Return the averaged solution at each stage instead of the last solution (ablation)Stagewise SGD (V2) · CIFAR-10 and CIFAR-100training errorHurt
Use explicit regularization at each stage and return the last solution (ablation)Stagewise SGD (V1) · CIFAR-10 and CIFAR-100testing errorImproved
Use an averaged solution at each stage rather than the last solution (ablation)START on convex losses · real-sim and E2006-tfidftesting errorNo 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