Research map / Optimization / Nonconvex and smooth optimization
Corner Gradient Descent
Dmitry Yarotsky
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 |
|---|---|---|---|
| apply Corner SGD (theta=1.8, memory 5) instead of plain SGD | SGD · synthetic indicator problem | loss convergence exponent: 0.25 -> 0.45 (theoretical) | Improved |
| apply Corner SGD with theta=1.3 instead of plain SGD | SGD · MNIST, batch size 1000 and 100 | loss convergence exponent: factor ~1.5 | Improved |
| raise theta from 1.3 to 1.8 (ablation) | Corner SGD · MNIST, batch size 1000 | acceleration factor: 1.5 -> 1.5 | No clear effect |
| raise theta from 1.3 to 1.8 (ablation) | Corner SGD · MNIST, batch size 1000 | training loss | Improved |
| raise theta from 1.3 to 1.8 (ablation) | Corner SGD · MNIST, batch size 100 | stability | Hurt |
Closest papers by meaning
- SGD with memory: fundamental properties and stochastic acceleration (ICLR 2025 · similarity 0.89)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.86)
- Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters (NeurIPS 2026 · similarity 0.86)
- Toward a Unified Theory of Gradient Descent under Generalized Smoothness (ICML 2025 · similarity 0.86)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.86)
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime (NeurIPS 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.
