Research map / Optimization / Nonconvex and smooth optimization
Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms
Tao Sun, Penghang Yin, Dongsheng Li, Chun Huang, Lei Guan, Hao Jiang
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 restricted strong convexity rather than strong convexity | Heavy-ball · Restricted strongly convex objectives | objective-gap convergence rate: linear convergence | Improved |
| Use stochastic uniform block selection | Heavy-ball · Smooth convex multi-block objectives | gradient norm: o(1/√k) | Improved |
| Increase the inertial parameter β from 0 to values up to 0.4 | Heavy-ball and cyclic coordinate descent Heavy-ball · Linear regression and logistic regression with Gaussian and Bernoulli data | convergence speed | Improved |
| Add inertia to stochastic block coordinate descent | Stochastic coordinate descent Heavy-ball · Linear regression and logistic regression | convergence speed | No clear effect |
Closest papers by meaning
- Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization (ICLR 2025 · similarity 0.89)
- Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise (ICLR 2024 · similarity 0.87)
- Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games (ICML 2025 · similarity 0.86)
- Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization (ICML 2025 · similarity 0.85)
- Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance (ICLR 2025 · similarity 0.85)
- Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis (NeurIPS 2025 · similarity 0.84)
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.
