Research map / Learning theory and algorithms / Sample complexity
Estimating Stochastic Linear Combination of Non-Linear Regressions
Di Wang, Xiangyu Guo, Chaowen Guan, Shi Li, Jinhui Xu
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 |
|---|---|---|---|
| increase sample size n from 100,000 to 500,000 | OLS/Stein-lemma estimator for linear combination of non-linear regressions · Synthetic data, polynomial/sigmoid/logistic links, p=20 | maximal relative error | Improved |
| use sub-sampled covariance with |S| >= 0.2n instead of |S| = n (ablation) | Sub-sampled covariance OLS estimator · Synthetic data, n=500,000, p=20 | maximal relative error | No clear effect |
| mix polynomial links of degrees x, x^3, x^5 in F | Proposed algorithm · Synthetic data, mixed link functions (Figure 4a) | maximal relative error | No clear effect |
| mix polynomial, logistic and log-exponential links in F | Proposed algorithm · Synthetic data, mixed link functions (Figure 4b) | maximal relative error | No clear effect |
Closest papers by meaning
- A convex optimization formulation for multivariate regression (NeurIPS 2020 · similarity 0.85)
- High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm (ICML 2017 · similarity 0.85)
- Layer-Wise Learning Strategy for Nonparametric Tensor Product Smoothing Spline Regression and Graphical Models (JMLR 2019 · similarity 0.85)
- Optimal Linear Regression Without a Variance (NeurIPS 2026 · similarity 0.85)
- Linear Regression using Heterogeneous Data Batches (NeurIPS 2024 · similarity 0.84)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.83)
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.
