Research map / Optimization / Optimizers
DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 iterate averaging (polynomial averaging, power 8) instead of last iterate | DoWG · CIFAR10 VGG11 and ResNet-50 | test accuracy | Helped |
| compare DoWG last iterate against Adam with cosine annealing | DoWG · CIFAR10 | test accuracy | Hurt |
| DoWG step size estimates larger than DoG | DoWG · CIFAR10 ResNet-50 | training stability | Hurt |
| use distance over weighted gradients instead of plain gradient sum in the step size | DoG · convex Lipschitz and smooth objectives | convergence rate | Helped |
Closest papers by meaning
- Tuning-Free Stochastic Optimization (ICML 2024 · similarity 0.88)
- Nesterov acceleration in benignly non-convex landscapes (ICLR 2025 · similarity 0.86)
- Gradient correlation is a key ingredient to accelerate SGD with momentum (ICLR 2025 · similarity 0.86)
- LPGD: A General Framework for Backpropagation through Embedded Optimization Layers (ICML 2024 · similarity 0.86)
- Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality (NeurIPS 2025 · similarity 0.86)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.86)
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.