AISTATS 2024poster4 citations

Random Oscillators Network for Time Series Processing

Andrea Ceni, Andrea Cossu, Maximilian W Stölzle, Jingyue Liu, Cosimo Della Santina, Davide Bacciu, Claudio Gallicchio

Abstract

We introduce the Random Oscillators Network (RON), a physically-inspired recurrent model derived from a network of heterogeneous oscillators. Unlike traditional recurrent neural networks, RON keeps the connections between oscillators untrained by leveraging on smart random initialisations, leading to exceptional computational efficiency. A rigorous theoretical analysis finds the necessary and sufficient conditions for the stability of RON, highlighting the natural tendency of RON to lie at the edge of stability, a regime of configurations offering particularly powerful and expressive models. Through an extensive empirical evaluation on several benchmarks, we show four main advantages of RON. 1) RON shows excellent long-term memory and sequence classification ability, outperforming other randomised approaches. 2) RON outperforms fully-trained recurrent models and state-of-the-art randomised models in chaotic time series forecasting. 3) RON provides expressive internal representations even in a small parametrisation regime making it amenable to be deployed on low-powered devices and at the edge. 4) RON is up to two orders of magnitude faster than fully-trained models.

BibTeX
@InProceedings{pmlr-v238-ceni24a,
  title = 	 {Random Oscillators Network for Time Series Processing},
  author =       {Ceni, Andrea and Cossu, Andrea and W St\"{o}lzle, Maximilian and Liu, Jingyue and Della Santina, Cosimo and Bacciu, Davide and Gallicchio, Claudio},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {4807--4815},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v238/ceni24a/ceni24a.pdf},
  url = 	 {https://proceedings.mlr.press/v238/ceni24a.html},
  abstract = 	 {We introduce the Random Oscillators Network (RON), a physically-inspired recurrent model derived from a network of heterogeneous oscillators. Unlike traditional recurrent neural networks, RON keeps the connections between oscillators untrained by leveraging on smart random initialisations, leading to exceptional computational efficiency. A rigorous theoretical analysis finds the necessary and sufficient conditions for the stability of RON, highlighting the natural tendency of RON to lie at the edge of stability, a regime of configurations offering particularly powerful and expressive models. Through an extensive empirical evaluation on several benchmarks, we show four main advantages of RON. 1) RON shows excellent long-term memory and sequence classification ability, outperforming other randomised approaches. 2) RON outperforms fully-trained recurrent models and state-of-the-art randomised models in chaotic time series forecasting. 3) RON provides expressive internal representations even in a small parametrisation regime making it amenable to be deployed on low-powered devices and at the edge. 4) RON is up to two orders of magnitude faster than fully-trained models.}
}