Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Toward Robust Uncertainty Estimation with Random Activation 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 different random activation functions across ensemble members instead of a shared activation function | Anchored Ensemble · 25 regression datasets | NLL | Helped |
| Use random activation functions with RP-param (ablation) | RP-param on Parkinson's · Parkinson's | NLL: >100 -> 48.66 | Helped |
| Increase the cardinality of the activation-function set (ablation) | RAFs Ensemble · Superconductivity | NLL | Helped |
| Vary the number of ensemble members (ablation) | RAFs Ensemble · PUMA560 | NLL | Mixed |
| Use RAFs rather than RP-param | Uncertainty estimation on Abalone · Abalone | NLL: 28.37 ± 0.10 -> 28.90 ± 0.10 | Hurt |
| Use RAFs rather than DE | Uncertainty estimation on Parkinson's · Parkinson's | NLL: 26.74 ± 0.02 -> 45.69 ± 0.16 | Hurt |
Closest papers by meaning
- Neural Ensemble Search for Uncertainty Estimation and Dataset Shift (NeurIPS 2021 · similarity 0.89)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.89)
- Uncertainty Quantification with the Empirical Neural Tangent Kernel (NeurIPS 2025 · similarity 0.87)
- Accurate Uncertainty Estimation and Decomposition in Ensemble Learning (NeurIPS 2019 · similarity 0.87)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.86)
- Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts (ICML 2024 · 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.