Under a Locally Spike Sparse model and idealized Random Forest assumptions, LocalLSSFind provably recovers the signed features and interactions driving a single test prediction.
Provable Boolean interaction recovery from tree ensemble obtained via random forests,
1 Pith paper cite this work, alongside 14 external citations. Polarity classification is still indexing.
1
Pith paper citing it
14
external citations · OpenAlex
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provable Recovery of Locally Important Signed Features and Interactions from Random Forest
Under a Locally Spike Sparse model and idealized Random Forest assumptions, LocalLSSFind provably recovers the signed features and interactions driving a single test prediction.