Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Introduces distributional random forests for joint posterior inference and an SMC update for the prior in ABC, claiming accurate posteriors across deterministic and stochastic models.
citing papers explorer
-
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
-
Approximate Bayesian Computation sequential Monte Carlo via random forests
Introduces distributional random forests for joint posterior inference and an SMC update for the prior in ABC, claiming accurate posteriors across deterministic and stochastic models.