Research map / Optimization / Nonconvex and smooth optimization
SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients
Feihu Huang, Junyi Li, Heng Huang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use SUPER-ADAM with tau=1 instead of SGD, Adam, Amsgrad, AdaGrad-Norm, Adam+, STORM, AdaBelief | SUPER-ADAM · CIFAR-10 ResNet-18 and CIFAR-100 VGG-19 | train/test error and accuracy | Improved |
| use SUPER-ADAM with tau=0 instead of Adam/Amsgrad | SUPER-ADAM · CIFAR-10 and CIFAR-100 | train/test error and accuracy | No clear effect |
| use SUPER-ADAM with tau=1 instead of other optimizers | SUPER-ADAM · ImageNet ResNet-34 | train/test error and accuracy | Improved |
| use SUPER-ADAM with tau=1 instead of other optimizers | SUPER-ADAM · WikiText-2 LSTM | train/test perplexity | Improved |
| use SUPER-ADAM with tau=0 instead of other Adam-type optimizers | SUPER-ADAM · WikiText-2 LSTM | train/test perplexity | No clear effect |
Closest papers by meaning
- Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration (JMLR 2022 · similarity 0.93)
- A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD (ICML 2025 · similarity 0.91)
- Adam with model exponential moving average is effective for nonconvex optimization (NeurIPS 2024 · similarity 0.90)
- MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent (ICML 2024 · similarity 0.89)
- Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold (NeurIPS 2025 · similarity 0.89)
- Prodigy: An Expeditiously Adaptive Parameter-Free Learner (ICML 2024 · similarity 0.87)
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.
