4 papers
Expectation-Maximization as a Spectrally Governed Relaxation Flow
Qiao Wang
The expectation--maximization (EM) algorithm combines global monotonicity, local linear convergence, and strong practical robustness, but these features are usually analyzed separa…
Relaxation Kernel, Spectral Dissipation, and Global Convergence of Blahut--Arimoto Dynamics
Qiao Wang
We develop a spectral theory for continuous- and discrete-time Blahut--Arimoto (BA) dynamics, centered on the relaxation kernel $ \G = \E_p[K^*_X \otimes K^*_X] $. Five main result…
Autocorrelation Reintroduces Spectral Bias in KANs for Time Series Forecasting
Chen Zeng, Jiahui Wang, Qiao Wang
Existing theory suggests that Kolmogorov-Arnold Networks (KANs) can overcome the spectral bias commonly observed in neural networks under the assumption that inputs are statistical…
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
Chen Zeng, Tiehang Xu, Qiao Wang
Traditional neural networks struggle to capture the spectral structure of complex signals. Fourier neural networks (FNNs) attempt to address this by embedding Fourier series compon…