Research map / Optimization / Nonconvex and smooth optimization
Adaptive Averaging in Accelerated Descent Dynamics
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 |
|---|---|---|---|
| Replace predetermined averaging weights with adaptive averaging | Accelerated mirror descent · Strongly convex quadratic on simplex | objective value convergence | Helped |
| Use adaptive averaging instead of gradient restarting | Accelerated mirror descent · Weakly convex, linear and KL objectives on simplex | objective value convergence | Helped |
| Use adaptive averaging instead of speed restarting | Accelerated mirror descent · Simplex-constrained examples in R3 | objective value convergence | Helped |
| Use adaptive averaging versus restarting heuristics | Accelerated mirror descent · Weakly convex example | Lyapunov function monotonicity | Helped |
| Apply any heuristic (adaptive averaging or restarting) versus original method | Accelerated mirror descent · Simplex examples | oscillation around minimizers | Helped |
| Apply restarting or adaptive averaging | Accelerated mirror descent · Simplex examples | energy function E_r | No clear effect |
Closest papers by meaning
- Acceleration and Averaging in Stochastic Descent Dynamics (NeurIPS 2017 · similarity 0.92)
- Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions (ICML 2018 · similarity 0.90)
- Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity (NeurIPS 2026 · similarity 0.87)
- Mirror Descent-Ascent for mean-field min-max problems (NeurIPS 2026 · similarity 0.87)
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 2024 · similarity 0.86)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · 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.