AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
By: Chen Zeng, Tiehang Xu, Qiao Wang
Potential Business Impact:
Predicts future events better than other computer brains.
Conventional neural networks frequently face challenges in spectral analysis of signals. To address this challenge, Fourier neural networks (FNNs) and similar approaches integrate components of Fourier series into the structure of neural networks. Nonetheless, a significant hurdle is often overlooked: the superposition of periodic signals does not necessarily result in a periodic signal. For example, when forecasting almost periodic functions composed of signals with incommensurate frequencies, traditional models such as Autoregressive Integrated Moving Average (ARIMA) frequently outperform most neural networks including large language models (LLMs). To tackle this goal, we propose Autoregressive-Weight-Enhanced AR-KAN, a hybrid model that combines the benefits of both methods. Using the Universal Myopic Mapping Theorem, we apply a Kolmogorov-Arnold Network (KAN) for the static nonlinear part and include memory through a pre-trained AR component, which can be explained to retain the most useful information while eliminating redundancy. Experimental data indicates that AR-KAN delivers superior results on $72\%$ of real-world datasets.
Similar Papers
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
Machine Learning (CS)
Predicts future events better than other smart programs.
A Primer on Kolmogorov-Arnold Networks (KANs) for Probabilistic Time Series Forecasting
Machine Learning (CS)
Predicts future traffic with less guessing.
Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints
Machine Learning (CS)
Predicts how tiny things move much faster.