Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Flexible Signal Denoising via Flexible Empirical Bayes Shrinkage
Zhengrong Xing, Peter Carbonetto, Matthew Stephens
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 SMASH instead of MFVB for mean estimation | joint mean-variance denoising · Simulated Gaussian data, Scenario 1 | MSE: 0.0330 -> 0.0334 | No clear effect |
| use SMASH instead of MFVB for s.d. estimation | joint mean-variance denoising · Simulated Gaussian data, Scenario 1 | MSE: 0.0199 -> 0.0187 | Improved |
| use SMASH instead of MFVB for mean estimation | joint mean-variance denoising · Simulated Gaussian data, Scenario 2 | MSE: 0.0172 -> 0.0158 | Improved |
| use SMASH instead of MFVB for s.d. estimation | joint mean-variance denoising · Simulated Gaussian data, Scenario 2 | MSE: 0.0085 -> 0.0065 | Improved |
| use SMASH variance estimate instead of RMAD with TI thresholding | TI thresholding · Simulated Gaussian data with abrupt variance changes | MISE | Improved |
| use SMASH (heteroskedastic) instead of EbayesThresh with homoskedastic variance | SMASH · Simulated Gaussian test functions | MISE | Improved |
| use SMASH instead of Haar-Fisz and BMSM | Poisson denoising · Simulated Poisson data, intensity ranges (1/100,3), (1/8,8), (1/128,128) | MISE | Improved |
| use SMASH instead of Haar-Fisz at high intensity | Poisson denoising · Simulated Poisson Spikes test function, high intensity | MISE | Hurt |
| use SMASH for ChIP-seq intensity estimation instead of Haar-Fisz | Poisson denoising · ChIP-seq YY1 data (131,072 sites) | peak recovery | Improved |
Closest papers by meaning
- Sampling Binary Data by Denoising through Score Functions (ICML 2025 · similarity 0.84)
- Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods (NeurIPS 2024 · similarity 0.83)
- On the Posterior Distribution in Denoising: Application to Uncertainty Quantification (ICLR 2024 · similarity 0.83)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.83)
- Provable Posterior Sampling with Denoising Oracles via Tilted Transport (NeurIPS 2024 · similarity 0.82)
- Adaptive Estimation and Learning under Temporal Distribution Shift (ICML 2025 · similarity 0.82)
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.
