Research map / Optimization / Nonconvex and smooth optimization
Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth 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 |
|---|---|---|---|
| Use accelerated proximal extragradient with online-learned Hessian approximations instead of NAG | Smooth convex optimization · Smooth convex optimization, k = \Omega(d \log d) | optimality gap convergence rate: \mathcal{O}(1/k^2) -> \mathcal{O}\bigl(\frac{\sqrt{d\log k}}{k^{2.5}}\bigr) | Helped |
| Use accelerated proximal extragradient with online-learned Hessian approximations instead of NAG | Smooth convex optimization · Smooth convex optimization, k = \mathcal{O}(d) | optimality gap convergence rate: \mathcal{O}(1/k^2) -> \mathcal{O}(1/k^2) | No clear effect |
| Use A-QNPE instead of NAG | Logistic regression · Synthetic dataset | iterations to convergence | Helped |
| Use A-QNPE instead of BFGS | Logistic regression · Synthetic dataset | iterations to convergence | Hurt |
| Use A-QNPE instead of NAG | Logistic regression · Synthetic dataset | gradient queries to convergence | Helped |
| Use A-QNPE with online Hessian approximation updates | Smooth convex optimization · Smooth convex optimization | gradient queries per iteration: 3 | No clear effect |
Closest papers by meaning
- Stochastic Newton Proximal Extragradient Method (NeurIPS 2024 · similarity 0.91)
- Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm (ICML 2021 · similarity 0.90)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.89)
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion (ICML 2024 · similarity 0.89)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.88)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.88)
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.