Augmenting Kolmogorov-Arnold Networks with prediction exits at each layer improves accuracy and often yields more parsimonious models, and a differentiable learning-to-exit algorithm automates the choice of exit weights.
Physics-informed machine learning: case studies for weather and climate modelling,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
Augmenting Kolmogorov-Arnold Networks with prediction exits at each layer improves accuracy and often yields more parsimonious models, and a differentiable learning-to-exit algorithm automates the choice of exit weights.