Research map / Probabilistic and scientific modeling / Variational and generative sampling
Neural Empirical Bayes
Saeed Saremi, Aapo Hyvärinen
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 smooth ReLU activation z/(1+exp(-beta z)) with beta=1 instead of ReLU (ablation) | DEEN denoising network · MNIST denoising | training loss | Improved |
| use wide ConvNets instead of a fully connected network (ablation) | DEEN denoising network · MNIST denoising | denoising quality | Improved |
| overparameterize the linear output layer (ablation) | DEEN · MNIST training | convergence speed | Improved |
Closest papers by meaning
- Function-Space Regularization in Neural Networks: A Probabilistic Perspective (ICML 2023 · similarity 0.87)
- Bayesian Online Natural Gradient (BONG) (NeurIPS 2024 · similarity 0.86)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.86)
- Optimization and Bayes: A Trade-off for Overparameterized Neural Networks (NeurIPS 2023 · similarity 0.86)
- Covariate-Powered Empirical Bayes Estimation (NeurIPS 2019 · similarity 0.86)
- Sampling Binary Data by Denoising through Score Functions (ICML 2025 · 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.
