Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions
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 |
|---|---|---|---|
| Use DJ rather than MCDP | Regression uncertainty estimates · Yacht | AUPRC: 0.67 ± 0.06 -> 0.87 ± 0.05 | Helped |
| Use DJ rather than MCDP | Regression uncertainty estimates · Housing | AUPRC: 0.86 ± 0.00 -> 0.80 ± 0.04 | Hurt |
| Use DJ rather than MCDP | Regression uncertainty estimates · Energy | AUPRC: 0.84 ± 0.03 -> 0.77 ± 0.08 | Hurt |
| Use DJ rather than BNN | Regression uncertainty estimates · Kin8nm | AUPRC: 0.89 ± 0.00 -> 0.88 ± 0.01 | Hurt |
| Use DJ rather than MCDP | Regression uncertainty estimates · Yacht | MSE: 150.93 -> 26.55 | Helped |
| Use DJ rather than MCDP | Regression uncertainty estimates · Housing | MSE: 113.04 -> 33.87 | Helped |
| Use DJ rather than MCDP | Regression uncertainty estimates · Energy | MSE: 92.57 -> 11.06 | Helped |
| Use DJ rather than BNN | Regression uncertainty estimates · Kin8nm | MSE: 0.68 -> 0.00 | Helped |
| Use DJ rather than PBP | Regression uncertainty estimates · Housing | coverage: 5.0% -> 99.8% | Helped |
| Use second-order influence terms instead of first-order terms only (ablation) | DJ confidence intervals · Normal-feature synthetic regression | discrimination | Helped |
Closest papers by meaning
- Locally Valid and Discriminative Prediction Intervals for Deep Learning Models (NeurIPS 2021 · similarity 0.91)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.90)
- Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections (NeurIPS 2019 · similarity 0.89)
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows (NeurIPS 2025 · similarity 0.89)
- Uncertainty Quantification with the Empirical Neural Tangent Kernel (NeurIPS 2025 · similarity 0.88)
- SURE: SUrvey REcipes for building reliable and robust deep 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.