Research map / Optimization / Optimizers
Escaping Saddle Points Faster with Stochastic Momentum
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 |
|---|---|---|---|
| Increase the momentum parameter β | SGD with stochastic heavy-ball momentum · Saddle-point escape | escape iterations: T_thred = O( (1-β) log( 1 / ((1-β)ε) ) ε^{-6} ) | Helped |
| Use stochastic heavy-ball momentum instead of standard SGD (β = 0) | The two synthetic saddle-point objectives, including phase retrieval · Two constructed stochastic optimization tasks | convergence speed | Helped |
Closest papers by meaning
- The Marginal Value of Momentum for Small Learning Rate SGD (ICLR 2024 · similarity 0.92)
- Random Scaling and Momentum for Non-smooth Non-convex Optimization (ICML 2024 · similarity 0.90)
- Gradient correlation is a key ingredient to accelerate SGD with momentum (ICLR 2025 · similarity 0.90)
- On the Performance Analysis of Momentum Method: A Frequency Domain Perspective (ICLR 2025 · similarity 0.88)
- Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration (NeurIPS 2026 · similarity 0.88)
- Dimension-adapted Momentum Outscales SGD (NeurIPS 2025 · 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.