# Neural Decomposition of Time-Series Data for Effective Generalization

arXiv: https://arxiv.org/abs/1705.09137 · HTML: https://mlsanity.com/paper/1705.09137/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 9 of 9)

- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices](https://mlsanity.com/paper/2203.10716/) (2022)
- [A Survey on Deep Learning based Time Series Analysis with Frequency Transformation](https://mlsanity.com/paper/2302.02173/) (2023)
- [Learning Deep Time-index Models for Time Series Forecasting](https://mlsanity.com/paper/2207.06046/) (2022)
- [Out-of-Distribution Generalization in Time Series: A Survey](https://mlsanity.com/paper/2503.13868/) (2025)
- [Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks](https://mlsanity.com/paper/1903.05697/) (2019)
- [Task-Synchronized Recurrent Neural Networks](https://mlsanity.com/paper/2204.05192/) (2022)
- [Improving the Transferability of Time Series Forecasting with Decomposition Adaptation](https://mlsanity.com/paper/2307.00066/) (2023)
- [Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting](https://mlsanity.com/paper/2609.29317/) (2026)

## Abstract (arXiv)

We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used to perform a Fourier-like decomposition of training samples into a sum of sinusoids, augmented by units with nonperiodic activation functions to capture linear trends and other nonperiodic components. We show how careful weight initialization can be combined with regularization to form a simple model that generalizes well. Our method generalizes effectively on the Mackey-Glass series, a dataset of unemployment rates as reported by the U.S. Department of Labor Statistics, a time-series of monthly international airline passengers, the monthly ozone concentration in downtown Los Angeles, and an unevenly sampled time-series of oxygen isotope measurements from a cave in north India. We find that ND outperforms popular time-series forecasting techniques including LSTM, echo state networks, ARIMA, SARIMA, SVR with a radial basis function, and Gashler and Ashmore's model.