Research map / Optimization / Optimizers
The Lingering of Gradients: How to Reuse Gradients Over Time
Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang
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 SVRGlin (reuse gradients within lingering radii) instead of SVRG/SAGA | SVRG · Yahoo! Front Page revenue maximization LP (dual) | gradient computations per epoch | Improved |
| use SVRGlin instead of SVRG/SAGA during first 5-7 passes | SVRG · Yahoo! Front Page revenue maximization LP (dual) | gradient computations | No clear effect |
| use SVRGlin instead of SVRG/SAGA | SVRG · Yahoo! Front Page revenue maximization LP (dual) | optimization error per epoch | No clear effect |
| use SVRGlin instead of SVRG/SAGA | SVRG · Yahoo! Front Page revenue maximization LP (primal) | primal error | Improved |
Closest papers by meaning
- The Complexity of Finding Stationary Points with Stochastic Gradient Descent (ICML 2020 · similarity 0.87)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.87)
- Gradient Descent Can Take Exponential Time to Escape Saddle Points (NeurIPS 2017 · similarity 0.86)
- Asymptotic theory of SGD with a general learning-rate (NeurIPS 2025 · similarity 0.86)
- Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions (NeurIPS 2019 · similarity 0.86)
- Learning Complexity of Gradient Descent and Conjugate Gradient Algorithms (AAAI 2025 · similarity 0.85)
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.
