Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
The Unreasonable Effectiveness of Deep Evidential Regression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Normalize residuals by the predicted t-distribution width in the regularizer | DER · Binary Pulse | uncertainty estimation quality | Helped |
| Replace the original epistemic uncertainty proxy with the redefined proxy 1/sqrt(nu) | DER · NYU Depth v2 | epistemic uncertainty separation | Hurt |
| Use the t-distribution width as the uncertainty proxy | DER · NYU Depth v2 | separation of aleatoric and epistemic uncertainty | Hurt |
| Normalize residuals by the predicted t-distribution width in the regularizer (ablation) | DER · Synthetic cubic regression | uncertainty prediction | No clear effect |
| Replace the t-distribution likelihood with a normal likelihood (ablation) | DER · Synthetic cubic regression | sample variance | Hurt |
| Set lambda to 0 and use the normal-distribution standard deviation as an uncertainty proxy (ablation) | DER depth estimation · NYU Depth v2 | separation of in-distribution and out-of-distribution data | Helped |
Closest papers by meaning
- Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods? (ICML 2024 · similarity 0.93)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.92)
- Uncertainty Regularized Evidential Regression (AAAI 2024 · similarity 0.92)
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.90)
- The Evidence Contraction Issue in Deep Evidential Regression: Discussion and Solution (AAAI 2024 · similarity 0.89)
- Epistemic Uncertainty Quantification For Pre-Trained Neural Networks (CVPR 2024 · similarity 0.87)
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.