Research map / Optimization / Optimizers
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtárik, Michael W. Mahoney, Martin Takac
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 OASIS with a fixed learning rate and no first moment instead of SGD (ablation) | OASIS · CIFAR10, ResNet-32 | accuracy: 92.85 -> 93.01 | Improved |
| use OASIS with a fixed learning rate and no first moment instead of SGD (ablation) | OASIS · CIFAR10, ResNet-20 | accuracy: 92.02 -> 91.96 | No clear effect |
| use OASIS with adaptive learning rate instead of SGD | OASIS · CIFAR100, ResNet-18 | accuracy: 76.57 -> 76.93 | Improved |
| add gradient momentum to OASIS with fixed learning rate (ablation) | OASIS · CIFAR10, ResNet-20 | accuracy: 91.96 -> 92.01 | No clear effect |
| add gradient momentum to OASIS with fixed learning rate (ablation) | OASIS · CIFAR10, ResNet-32 | accuracy: 93.01 -> 92.77 | Hurt |
| add gradient momentum to OASIS with fixed learning rate (ablation) | OASIS · CIFAR100, ResNet-18 | accuracy: 76.28 -> 76.89 | Improved |
| add gradient momentum to OASIS (ablation) | OASIS · CIFAR10 training, early stages | training curve | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- AdaHessian — ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning (AAAI 2021) · better on 0 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization (NeurIPS 2025 · similarity 0.88)
- Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent (ICML 2025 · similarity 0.88)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.87)
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness (ICLR 2024 · similarity 0.87)
- Structured Preconditioners in Adaptive Optimization: A Unified Analysis (ICML 2025 · similarity 0.86)
- Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits (NeurIPS 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.
