TSL learns separable rank-1 univariate function products via stagewise greedy fitting with orthogonal refitting, reconstructible from first-order partial dependence plots with approximation guarantees.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Additive Decompositions: Interpretability Through Separability
TSL learns separable rank-1 univariate function products via stagewise greedy fitting with orthogonal refitting, reconstructible from first-order partial dependence plots with approximation guarantees.