Research map / Learning theory and algorithms / Sample complexity
Instability, Computational Efficiency and Statistical Accuracy
Nhat Ho, Koulik Khamaru, Raaz Dwivedi, Martin J. Wainwright, Michael I. Jordan, Bin Yu
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 |
|---|---|---|---|
| replace gradient descent with Newton's method | non-linear regression with g(t)=t^2 · Non-linear regression g(t)=t^2, d=1 (simulation) | iteration complexity: n^{1/2} -> log n | Improved |
| replace gradient descent with cubic-regularized Newton's method | non-linear regression with g(t)=t^2 · Non-linear regression g(t)=t^2, d=1 (simulation) | iteration complexity: n^{1/2} -> n^{1/6} | Improved |
| replace gradient descent with Newton's method or cubic-regularized Newton | non-linear regression with g(t)=t^2 · Non-linear regression g(t)=t^2, d=1 (simulation) | statistical error rate: n^{-1/4} -> n^{-1/4} | No clear effect |
Closest papers by meaning
- Toward Better Generalization Bounds with Locally Elastic Stability (ICML 2021 · similarity 0.86)
- Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization (JMLR 2018 · similarity 0.86)
- Stability and L2-penalty in Model Averaging (JMLR 2024 · similarity 0.85)
- Generalization Error Bounds for Optimization Algorithms via Stability (AAAI 2017 · similarity 0.85)
- Stochastic Gradient Methods: Bias, Stability and Generalization (JMLR 2026 · similarity 0.85)
- Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems (NeurIPS 2026 · similarity 0.84)
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.
