4 papers · 1 filter
FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization
Kazi Ahmed Asif Fuad, Lizhong Chen
Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions, increasing flexibility but also parameter memory because each edge stores multip…
BiKAN: Restoring Collapsed Basis of Binary Kolmogorov--Arnold Networks
Kazi Ahmed Asif Fuad, Lizhong Chen
Binarizing a polynomial Kolmogorov--Arnold Network (KAN) not only changes parameter precision, but also alters the function space available to each layer. When activations are rest…
SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits
Kazi Ahmed Asif Fuad, Lizhong Chen
Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions parameterized by multiple basis coefficients. This introduces a source of redunda…
QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks
Kazi Ahmed Asif Fuad, Lizhong Chen
Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to hetero…