Research map / Optimization / Optimizers
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin Liang
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 |
|---|---|---|---|
| Adapt epoch batch size using average stochastic gradients from the preceding epoch | SVRG and SpiderBoost · a8a, a9a, w8a, ijcnn1 | gradient evaluations to convergence | Improved |
| Adapt epoch batch size using average stochastic gradients from the preceding epoch | SVRPG and SPIDER-PG · InvertedPendulum, InvertedDoublePendulum, Swimmer, Hopper | convergence speed | Improved |
| Adapt batch size from history gradients instead of using prescribed exponential or linear growth (ablation) | SpiderBoost · a9a | loss versus gradient evaluations | Improved |
| Adapt batch size from history gradients instead of using prescribed growth (ablation) | SpiderBoost · w8a | loss versus gradient evaluations | Mixed |
| Use exponentially increasing batch size rather than linearly increasing batch size (ablation) | SpiderBoost · a9a and w8a | loss versus gradient evaluations | Mixed |
| Adapt batch size from history gradients | AbaSVRG · MNIST three-layer neural network | training loss | Improved |
| Adapt batch size from history gradients | AbaSPIDER · MNIST three-layer neural network | gradient norm | Improved |
Closest papers by meaning
- Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients (JMLR 2025 · similarity 0.87)
- Stochastic Variance-Reduced Policy Gradient (ICML 2018 · similarity 0.87)
- Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching (ICML 2025 · similarity 0.86)
- MARS: Unleashing the Power of Variance Reduction for Training Large Models (ICML 2025 · similarity 0.86)
- Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation (ICML 2024 · similarity 0.86)
- Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization (AAAI 2024 · 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.
