2024-04-18-ceni24a.md

title	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Random Oscillators Network for Time Series Processing	https://github.com/AndreaCossu/RandomizedCoupledOscillators	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.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	ceni24a	0	Random Oscillators Network for Time Series Processing	4807	4815	4807-4815	4807	false	Ceni, Andrea and Cossu, Andrea and W St\"{o}lzle, Maximilian and Liu, Jingyue and Della Santina, Cosimo and Bacciu, Davide and Gallicchio, Claudio	given family Andrea Ceni given family Andrea Cossu given family Maximilian W Stölzle given family Jingyue Liu given family Cosimo Della Santina given family Davide Bacciu given family Claudio Gallicchio	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/ceni24a/ceni24a.pdf