Research map / Learning theory and algorithms / Matrix and tensor methods
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation
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 |
|---|---|---|---|
| Adaptively alternate Exploration and Exploitation rather than using Exploration alone | Hybrid · Limited-observation sparse linear regression | sample complexity: \widetilde{O} \left( \frac{ds_*^2}{s'} + \left( \frac{s_*}{r_{\mathrm{min}}^2} \land \frac{ds_*}{s'} \right) \frac{\sigm | Helped |
| Use iterative hard thresholding during training to keep updates sparse | Exploration · Limited-observation sparse linear regression | sample complexity: \widetilde{O} \left( \frac{ds_*^2}{s'} + \frac{d s_*}{s'} \frac{\sigma^2}{\varepsilon} \right) | Helped |
| Use Hybrid instead of Dantzig | Limited-observation sparse linear regression · Synthetic dataset | test mean squared error | Helped |
| Use Hybrid instead of RDA | Limited-observation sparse linear regression · Synthetic dataset | test mean squared error | Helped |
| Use Hybrid instead of Dantzig or RDA | Limited-observation sparse linear regression · CT-slice | test mean squared error | Helped |
Closest papers by meaning
- An Effective Hard Thresholding Method Based on Stochastic Variance Reduction for Nonconvex Sparse Learning (AAAI 2020 · similarity 0.91)
- Efficient Stochastic Gradient Hard Thresholding (NeurIPS 2018 · similarity 0.91)
- Learning Sparse Distributions using Iterative Hard Thresholding (NeurIPS 2019 · similarity 0.89)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.88)
- Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations (NeurIPS 2024 · similarity 0.87)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 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.