Research map / Probabilistic and scientific modeling / Variational and generative sampling
A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family
Trambak Banerjee, Qiang Liu, Gourab Mukherjee, Wengunag Sun
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 NEB instead of KM | Poisson compound estimation · Poisson Scenario 3, scaled loss | risk ratio: 1.17 | Improved |
| use NEB instead of BGR | Poisson compound estimation · Poisson Scenario 4, squared error | risk ratio: 1.15 | Improved |
| use NEB instead of TF OR under model misspecification | Poisson compound estimation · Poisson Scenario 3, squared error | risk ratio: 1.66 | Improved |
| use oracle bandwidth (NEB OR) instead of ARE-selected bandwidth | NEB · Poisson Scenario 3 | risk ratio: 1.00 -> 0.90 | Improved |
| use NEB instead of TF Gauss | Binomial odds estimation · Binomial Scenario 2, scaled loss | risk ratio: 1.51 | Improved |
| use NEB instead of TF OR | Binomial odds estimation · Binomial all scenarios | risk ratio: >10 | Improved |
| use NEB instead of TF Gauss on Poisson scenario 1 with squared error | Poisson compound estimation · Poisson Scenario 1, squared error | risk ratio: 1.00 | No clear effect |
| use NEB instead of TF Gauss on juvenile delinquency data, squared error | Poisson real data · Juvenile delinquency, k=0 | risk ratio: 1.01 | No clear effect |
| use NEB instead of KM on juvenile delinquency data, scaled loss | Poisson real data · Juvenile delinquency, k=1 | risk ratio: 1.19 | Improved |
| use NEB instead of KM on LinkedIn news data | Binomial odds real data · News Microsoft/LinkedIn, k=0 | risk ratio: 59.64 | Improved |
| use NEB instead of TF OR on Facebook news data | Binomial odds real data · News Economy/Facebook, k=1 | risk ratio: 81.57 | Improved |
Closest papers by meaning
- A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression (JMLR 2024 · similarity 0.86)
- Density Estimation in Infinite Dimensional Exponential Families (JMLR 2017 · similarity 0.85)
- A Computationally Efficient Method for Learning Exponential Family Distributions (NeurIPS 2021 · similarity 0.85)
- Covariate-Powered Empirical Bayes Estimation (NeurIPS 2019 · similarity 0.85)
- The Expxorcist: Nonparametric Graphical Models Via Conditional Exponential Densities (NeurIPS 2017 · similarity 0.85)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.83)
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.
