Research map / Optimization / Optimizers
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
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 |
|---|---|---|---|
| scale learning rate by sqrt(kappa) and adjust adaptive hyperparameters when increasing batch size from 256 to 8192 | Adam and RMSprop · CIFAR-10 VGG-16 and ResNet-50 | test accuracy: at most 3% | No clear effect |
| apply square root scaling rule to large batch training | Adam/RMSprop · Large-scale vision | test accuracy: 1.5% | No clear effect |
| apply square root scaling rule to large batch training | Adam/RMSprop · Large-scale language modeling (GPT on WikiText-103) | perplexity: 0.5 | No clear effect |
| simulate Adam SDE with SVAG up to ell=8 instead of discrete trajectory (ell=1) | Adam, ResNet-50 · CIFAR-10 | test accuracy and test functions | No clear effect |
Closest papers by meaning
- Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise (ICLR 2025 · similarity 0.92)
- A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD (ICML 2025 · similarity 0.90)
- Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks (NeurIPS 2025 · similarity 0.88)
- Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold (NeurIPS 2025 · similarity 0.88)
- Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation (NeurIPS 2024 · similarity 0.88)
- Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling (NeurIPS 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.