Deep-Koopman-KANDy recovers symbolic Koopman dictionaries post-training by replacing the encoder and decoder with KANs and applying a level-set construction with chain-rule gradients, achieving high recall on Lorenz and expected behavior on other maps.
This yields a one-dimensional dataset{(g j, q j)}N j=1 whereg j =g k(xj)andq j ≈h ′ k(gj)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.DS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
Deep-Koopman-KANDy recovers symbolic Koopman dictionaries post-training by replacing the encoder and decoder with KANs and applying a level-set construction with chain-rule gradients, achieving high recall on Lorenz and expected behavior on other maps.