Research map / Optimization / Nonconvex and smooth optimization
Optimal and Adaptive Monteiro-Svaiter Acceleration
Yair Carmon, Danielle Hausler, Arun Jambulapati, Yujia Jin, Aaron Sidford
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 |
|---|---|---|---|
| remove bisection from MS acceleration (ablation) | MS acceleration with cubic regularization oracle · logistic regression, a9a | convergence (qualitative) | Improved |
| MS acceleration with careful bisection versus plain cubic regularization and accelerated CR (ablation) | cubic regularization oracle · logistic regression, a9a | convergence (qualitative) | Improved |
| use lazy adaptive oracle inside the new acceleration scheme (ablation) | adaptive MS-Newton oracle · logistic regression, a9a | convergence (qualitative) | Improved |
| replace accelerated methods by Newton's method (ablation) | adaptive accelerated second-order methods · logistic regression, a9a | convergence (qualitative) | Improved |
| simply iterate the adaptive oracle without momentum (ablation) | adaptive MS-Newton oracle · logistic regression, a9a | convergence (qualitative) | Improved |
| add momentum to adaptive oracle (ablation) | adaptive MS-Newton oracle · lower-bound construction | convergence (qualitative) | No clear effect |
| add momentum to cubic regularization with conservative M (ablation) | cubic regularization oracle · lower-bound construction | convergence (qualitative) | Improved |
| iterate first-order adaptive oracle versus L-BFGS (ablation) | first-order adaptive oracle · logistic regression | convergence (qualitative) | No clear effect |
Closest papers by meaning
- Adaptive Gradient Methods for Constrained Convex Optimization and Variational Inequalities (AAAI 2021 · similarity 0.87)
- Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations (ICML 2023 · similarity 0.87)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.87)
- Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique (ICML 2024 · similarity 0.87)
- Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization (NeurIPS 2025 · similarity 0.86)
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness (ICLR 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.
