AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients

Feihu Huang, Junyi Li, Heng Huang

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Complexity of nonconvex first-order methods · 8 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 SUPER-ADAM with tau=1 instead of SGD, Adam, Amsgrad, AdaGrad-Norm, Adam+, STORM, AdaBeliefSUPER-ADAM · CIFAR-10 ResNet-18 and CIFAR-100 VGG-19train/test error and accuracyImproved
use SUPER-ADAM with tau=0 instead of Adam/AmsgradSUPER-ADAM · CIFAR-10 and CIFAR-100train/test error and accuracyNo clear effect
use SUPER-ADAM with tau=1 instead of other optimizersSUPER-ADAM · ImageNet ResNet-34train/test error and accuracyImproved
use SUPER-ADAM with tau=1 instead of other optimizersSUPER-ADAM · WikiText-2 LSTMtrain/test perplexityImproved
use SUPER-ADAM with tau=0 instead of other Adam-type optimizersSUPER-ADAM · WikiText-2 LSTMtrain/test perplexityNo 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