Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Posterior Concentration for Sparse Deep Learning
Nicholas G Polson, Veronika Ročková
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 hierarchical priors on network width and sparsity instead of fixing them using known smoothness | SS-DL · α-Hölder regression functions | posterior concentration rate: ε_n=n^{-α/(2α+p)}log^δ(n) | Improved |
| Use a deep 11-layer, 39-unit network instead of a shallow 1-layer, 2048-unit network | ReLU network on the polynomial regression example · Polynomial regression example | MSE(validation): 0.09 -> 0.0112 | Improved |
| Use a deep 11-layer, 39-unit network instead of a shallow 1-layer, 2048-unit network | ReLU network on the polynomial regression example · Polynomial regression example | MSE(train): 0.0441 -> 0.0229 | Improved |
| Place complexity priors on width and sparsity | SS-DL · α-Hölder regression functions | posterior probability of oversized width or sparsity: Π(N>N_n|Y^(n))→0; Π(s>s_n|Y^(n))→0 | Improved |
Closest papers by meaning
- Posterior Concentrations of Fully-Connected Bayesian Neural Networks with General Priors on the Weights (JMLR 2025 · similarity 0.88)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.86)
- A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training (NeurIPS 2024 · similarity 0.86)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.85)
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification (NeurIPS 2025 · similarity 0.85)
- Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces (NeurIPS 2026 · similarity 0.85)
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.
