Research map / Optimization / Nonconvex and smooth optimization
Nesterov's Acceleration for Approximate Newton
Haishan Ye, Luo Luo, Zhihua Zhang
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 |
|---|---|---|---|
| add Nesterov acceleration to regularized sub-sampled Newton (ARSSN vs RSSN) | regularized sub-sampled Newton · gisette ridge regression, |S| = 1%n, 5%n, 10%n | convergence rate | Improved |
| increase sub-sample size from 5%n to 10%n | ARSSN · gisette ridge regression | iterations to reach 10^-14 error: 6000 -> 3000 | Improved |
| use ARSSN instead of accelerated gradient descent (adds curvature information) | AGD · logistic regression, six LIBSVM datasets, |S| = 1%n | convergence rate | Improved |
| use ARSSN instead of SVRG with small regularizer lambda=10^-2/n | SVRG · logistic regression, LIBSVM datasets | convergence rate | Improved |
| use ARSSN instead of SVRG with lambda=10^-1 | SVRG · sido0, rcv1, real-sim, avazu, gisette, svhn | convergence rate | Mixed |
| ARSSN on ill-conditioned problem (lambda=10^-2/n) versus other algorithms | ARSSN · gisette, sido0, svhn | convergence | Improved |
Closest papers by meaning
- On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic Settings (ICML 2020 · similarity 0.92)
- Approximate Newton Methods (JMLR 2021 · similarity 0.91)
- Approximate Newton Methods and Their Local Convergence (ICML 2017 · similarity 0.91)
- Nesterov acceleration despite very noisy gradients (NeurIPS 2024 · similarity 0.89)
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness (ICLR 2024 · similarity 0.89)
- Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates (NeurIPS 2026 · similarity 0.87)
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.
