Research map / Optimization / Nonconvex and smooth optimization
Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization
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 binary-search-based AGD with continuized Nesterov acceleration (one gradient per iteration, no function evaluations) | quasar convex minimization · theory, L-smooth rho-quasar convex | gradient-call complexity: removes log(1/(rho eps)) factor | Helped |
| continuized acceleration vs. AGD with binary search in number of gradient calls and CPU time on GLM experiments | GLM empirical risk (logistic, ReLU, quadratic) · synthetic n=1000, d=50 | gradient calls and CPU time | Helped |
| continuized acceleration vs. AGD in iterations | GLM empirical risk · synthetic n=1000, d=50 | function value vs iteration | No clear effect |
| accelerated stochastic GLMtron (continuized) vs stochastic GLMtron | learning Leaky-ReLU GLM · synthetic Leaky-ReLU | distance to w* | Helped |
Closest papers by meaning
- Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition (NeurIPS 2024 · similarity 0.91)
- How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization (ICML 2024 · similarity 0.89)
- Nesterov acceleration in benignly non-convex landscapes (ICLR 2025 · similarity 0.87)
- Nesterov acceleration despite very noisy gradients (NeurIPS 2024 · similarity 0.86)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · similarity 0.86)
- Gradient correlation is a key ingredient to accelerate SGD with momentum (ICLR 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.