Research map / Optimization / Nonconvex and smooth optimization
Adaptive Accelerated Gradient Converging Method under H\"{o}lderian Error Bound Condition
Mingrui Liu, Tianbao Yang
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 adaAGC instead of PG | squared hinge loss with ℓ1 regularization · splice (ε=10^-4) | proximal mappings: 2201 -> 2123 | Improved |
| Use adaAGC instead of PG | squared hinge loss with ℓ1 regularization · german.numer (ε=10^-4) | proximal mappings: 1014 -> 762 | Improved |
| Use adaAGC instead of PG | square loss with ℓ1 regularization · bodyfat (ε=10^-4) | proximal mappings: 366637 -> 15414 | Improved |
| Use adaAGC instead of PG | square loss with ℓ1 regularization · cpusmall (ε=10^-4) | proximal mappings: 109298 -> 9571 | Improved |
| Use adaAGC instead of PG | Huber loss with ℓ1 regularization · bodyfat (ε=10^-4) | proximal mappings: 258723 -> 16976 | Improved |
| Use adaAGC instead of PG | Huber loss with ℓ1 regularization · cpusmall (ε=10^-4) | proximal mappings: 74387 -> 26958 | Improved |
| Use adaAGC instead of PG | squared hinge loss with ℓ∞ regularization · splice (ε=10^-4) | proximal mappings: 3514 -> 2336 | Improved |
| Use adaAGC instead of PG | squared hinge loss with ℓ∞ regularization · german.numer (ε=10^-4) | proximal mappings: 898 -> 742 | Improved |
| Use adaAGC instead of PG | square loss with ℓ∞ regularization · bodyfat (ε=10^-4) | proximal mappings: 542414 -> 23226 | Improved |
| Use adaAGC instead of PG | square loss with ℓ∞ regularization · cpusmall (ε=10^-4) | proximal mappings: 139505 -> 10828 | Improved |
| Use adaAGC instead of PG | Huber loss with ℓ∞ regularization · bodyfat (ε=10^-4) | proximal mappings: 419316 -> 15744 | Improved |
| Use adaAGC instead of PG | Huber loss with ℓ∞ regularization · cpusmall (ε=10^-4) | proximal mappings: 75346 -> 27225 | Improved |
Closest papers by meaning
- Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization (NeurIPS 2023 · similarity 0.89)
- Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization (ICML 2017 · similarity 0.88)
- On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping (JMLR 2022 · similarity 0.88)
- Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems (NeurIPS 2019 · similarity 0.87)
- Adaptive Proximal Gradient Methods Are Universal Without Approximation (ICML 2024 · similarity 0.86)
- Adaptive Proximal Gradient Method for Convex Optimization (NeurIPS 2024 · 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.
