Statistical Modeling¶
Breiman, L. (2001). Statistical Modeling: The Two Cultures. Statistical Science, 16(3), 199-231.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Rashomon Effect
- In machine-learning interpretability, many models with very different internal logics achieve nearly identical accuracy on the same data, so the data does not privilege one explanation, and claims about "what the model learned" are licensed only at the level of the near-optimal-model set.
This sourceIntroduces the 'Rashomon' multiplicity: many models of very different form achieve near-identical accuracy on the same data, so the data does not privilege one explanation.
- In machine-learning interpretability, many models with very different internal logics achieve nearly identical accuracy on the same data, so the data does not privilege one explanation, and claims about "what the model learned" are licensed only at the level of the near-optimal-model set.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:f2bb057c7b73 · see in the full table