Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning under uncertainty: a comparison between R-W and Bayesian approach
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 |
|---|---|---|---|
| Increase learning rate eta in R-W model | R-W model · Simulated stable and low volatility | decision optimality | Mixed |
| Increase learning rate eta in R-W model | R-W model · Simulated high volatility | decision optimality | Helped |
| Increase learning rate eta in R-W model | R-W model · Simulated all volatility conditions | lose-shift rate | Helped |
| Increase belief of stationarity alpha in DBM | DBM · Simulated stable condition | decision optimality | Helped |
| Increase alpha toward 1 in DBM | DBM · Simulated low and high volatility | decision optimality | Mixed |
| Increase alpha in DBM | DBM · Simulated all volatility conditions | lose-shift rate | Mixed |
| Use DBM instead of R-W to fit behavior | Simulated Expert and WSLS agents · Low volatility N(30,1) | model accuracy: p = .000 | Helped |
| Use DBM instead of R-W to fit behavior | Simulated No Learning agents · Low volatility N(30,1) | model accuracy: p = .000 | Hurt |
| Use DBM instead of R-W | Human subjects · Stable condition | prediction accuracy: .81+/-.03 vs .81+/-.03 | No clear effect |
| Use DBM instead of R-W | Human poor learners · Low volatility N(30,1) | prediction accuracy: p = .000 | Hurt |
| Higher learning rate eta in human R-W fits | R-W model · Stable condition, human data | decision optimality | Hurt |
| Increase eta (R-W) in human low volatility data | R-W model · Low volatility N(30,1), human data | decision optimality | Mixed |
Closest papers by meaning
- Quantifying Uncertainty in the Presence of Distribution Shifts (NeurIPS 2025 · similarity 0.84)
- In-Context Learning Strategies Emerge Rationally (NeurIPS 2025 · similarity 0.83)
- Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs (ICML 2024 · similarity 0.83)
- Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification (ICML 2024 · similarity 0.82)
- Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning (NeurIPS 2026 · similarity 0.82)
- Inverse decision-making using neural amortized Bayesian actors (ICLR 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.