Research map / Learning theory and algorithms / Kernels and regression theory
Information theoretic limits of learning a sparse rule
Clément Luneau, jean barbier, Nicolas Macris
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 |
|---|---|---|---|
| use ReLU instead of linear activation at small noise variance | sparse generalized linear model · Delta in [0,0.5] | gamma_c (samples needed) | Improved |
| use ReLU instead of linear activation at large noise variance | sparse generalized linear model · large Delta | gamma_c (samples needed): a ≈ 5.87 vs 2 | Hurt |
| make sparsity and sampling rate vanishing instead of linear | asymptotic MMSE · Bernoulli and Bernoulli-Rademacher priors | MMSE | Improved |
| use GAMP algorithm instead of the Bayes-optimal estimator | sparse linear-sparsity regime · linear sparsity and sampling rate | MSE threshold | Hurt |
Closest papers by meaning
- Fundamental limits and algorithms for sparse linear regression with sublinear sparsity (JMLR 2023 · similarity 0.87)
- Bayes-optimal learning of an extensive-width neural network from quadratically many samples (NeurIPS 2024 · similarity 0.86)
- Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models (NeurIPS 2024 · similarity 0.85)
- Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks (NeurIPS 2026 · similarity 0.84)
- Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization (NeurIPS 2025 · similarity 0.84)
- A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples (ICML 2024 · 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.
