SparXnet is a sparse neural additive model with softmax feature selection and a generalization bound linear in selected features and logarithmic in total features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable Neural Networks with Guarantees: A Sparse Estimation Approach
SparXnet is a sparse neural additive model with softmax feature selection and a generalization bound linear in selected features and logarithmic in total features.