GRS-KAN integrates differentiable R-functions into KANs to explicitly encode geometric constraints, reducing test RMSE by up to 67% on discontinuity regression benchmarks.
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
-
Geometry-Aware R-Structured Kolmogorov-Arnold Networks
GRS-KAN integrates differentiable R-functions into KANs to explicitly encode geometric constraints, reducing test RMSE by up to 67% on discontinuity regression benchmarks.