A Dynamic Multiscale Anti-Aliasing Network for Time Series Forecasting

ICLR 2026 Conference Submission12877 Authors

Keywords: time series forecasting, frequency, aliasing

TL;DR: We propose a novel model named DMANet, a dynamic multiscale anti-aliasing network for time series forecasting tasks.

Abstract: Real-world time series inherently exhibit complex temporal patterns. Within chaotic systems, significant mixing and entanglement occur between different time-varying modes. Given that time series exhibit distinctly different patterns at various sampling scales, downsampling to extract multiscale features is a common approach. However, conventional downsampling causes high-frequency components in the original signal, those exceeding the new Nyquist frequency, to undergo spectral folding. This erroneously introduces spurious low-frequency patterns, perceived as low-frequency noise, thereby leading to the **aliasing problem**. To address this problem, we propose a Decomposition-Prevention-Fusion architecture framework called **DMANet**, which introduces the **D**ynamic **M**ultiscale **A**nti-Aliasing **Net**work. Specifically, DMANet comprises two key components: Multiscale Convolutional Downsampling, designed to capture temporal dependencies and inter-channel interactions, and an Anti-Aliasing Operation, which includes Pre-Sampling Anti-Aliasing Filtering and Post-Sampling Interpolation. These designs guarantee the fidelity of multiscale features before and after downsampling. We show that by mitigating the risk of aliasing, our proposed simple convolutional downsampling architecture achieves performance competitive with common baselines and larger Transformer-based models prevalent in existing studies across multiple benchmark datasets. Our codes are available at https://anonymous.4open.science/r/DMANet-ED7A.

Primary Area: learning on time series and dynamical systems

Submission Number: 12877