Research map / Learning theory and algorithms / Kernels and regression theory
Generalization and Estimation Error Bounds for Model-based Neural Networks
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 ISTA instead of a ReLU network | Sparse vector recovery · Simulated sparse vector recovery | estimation error | Helped |
| Use ISTA instead of a ReLU network | Sparse vector recovery · Simulated sparse vector recovery | L1 loss | Helped |
| Increase the soft-threshold value λ | ISTA network · Simulated sparse vector recovery with small training sets | estimation error | Helped |
| Increase the soft-threshold value λ | ISTA network · Simulated sparse vector recovery with large training sets | estimation error | No clear effect |
| Use a learned bias instead of a constant bias (ablation) | ISTA and ReLU networks · Simulated sparse vector recovery | estimation error | No clear effect |
| Use a learned bias instead of a constant bias (ablation) | ISTA and ReLU networks · Simulated sparse vector recovery | accuracy | No clear effect |
| Use soft-thresholding in place of ReLU | ISTA and ADMM networks · Sparse recovery | generalization error bound | Helped |
| Use soft-thresholding in place of ReLU | ISTA and ADMM networks · Sparse recovery | estimation error bound | Helped |
| Restrict weight norms to satisfy the stated design condition | ISTA network · Sparse recovery | generalization error | Helped |
Closest papers by meaning
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.89)
- Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks (ICML 2025 · similarity 0.89)
- Generalization Bounds for Rank-sparse Neural Networks (NeurIPS 2025 · similarity 0.87)
- Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.87)
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification (NeurIPS 2025 · similarity 0.87)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · 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.