analiza aiqbench
This study benchmarks Echo State Networks (ESNs) against standard statistical and deep learning models for time series forecasting, revealing that simple autoregressive ESNs offer competitive accuracy with significantly lower training overhead. The research highlights specific hyperparameter configurations, such as high leakage rates, that optimize performance across different data frequencies without the computational cost of complex recurrent architectures.
Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
arXiv:2602.03912v5 Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE), symmetric mean absolute percentage error (sMAPE), and the overall weighted average (OWA). The ESN is compared with simple benchmarks, statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS, as well as multilayer perceptron (MLP), recurrent neural network (RNN), and hybrid exponential smoothing-RNN (ES-RNN) benchmarks. The model-configuration analysis reveals frequency-specific patterns: monthly series tend to favor moderately persistent reservoirs, whereas quarterly series favor more contractive dynamics; across both frequencies, high leakage rates are generally preferred. In the final benchmark, the ESN performs on par with ARIMA and TBATS under mean MASE for monthly data and achieves the second-lowest mean MASE for quarterly data. ES-RNN provides the best aggregate accuracy for both frequencies. Overall, the results indicate that a simple autoregressive ESN can provide competitive forecast accuracy on the considered filtered M4 subsets, particularly under MASE, while requiring low training and forecasting time once the ESN configuration has been fixed.
Abstract:This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE), symmetric mean absolute percentage error (sMAPE), and the overall weighted average (OWA). The ESN is compared with simple benchmarks, statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS, as well as multilayer perceptron (MLP), recurrent neural network (RNN), and hybrid exponential smoothing-RNN (ES-RNN) benchmarks. The model-configuration analysis reveals frequency-specific patterns: monthly series tend to favor moderately persistent reservoirs, whereas quarterly series favor more contractive dynamics; across both frequencies, high leakage rates are generally preferred. In the final benchmark, the ESN performs on par with ARIMA and TBATS under mean MASE for monthly data and achieves the second-lowest mean MASE for quarterly data. ES-RNN provides the best aggregate accuracy for both frequencies. Overall, the results indicate that a simple autoregressive ESN can provide competitive forecast accuracy on the considered filtered M4 subsets, particularly under MASE, while requiring low training and forecasting time once the ESN configuration has been fixed.
Machine Learning (cs.LG)
arXiv:2602.03912 [cs.LG]
(or arXiv:2602.03912v5 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2602.03912 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 339 cuvinte
Subiecte conexe
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
A tensor network approach for chaotic time series prediction
arXiv · 17 iun. 2026
Echo Flow Networks
arXiv · 6 aug. 2026
Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning
arXiv · 16 iun. 2026