Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
This paper introduces MARO, a novel recurrent forecasting architecture that processes historical time series patches from most recent to oldest, using the former as an anchor to condition subsequent steps. This recurrent refinement approach allows for differential weighting of short-term and long-term history, addressing the uniform computational depth issue in existing models. MARO achieves state-of-the-art performance across various real-world time series datasets for both long-term and short-term forecasting.
Recurrently folding older time series context onto a most-recent anchor dramatically improves forecasting accuracy by naturally prioritizing recent evidence.
Long-term forecasting models commonly process all patches in a look-back window using the same fixed stack. Older contextual patches and recent evidence therefore receive the same computational depth. Yet the information closest to the forecast and the more distant context do not contribute equally. Uniform processing leaves this distinction unexpressed in the architecture. We propose MARO, a Most-Recent Anchoring with Recurrent Ordering model that processes the look-back window from the most recent patch to the oldest. The most recent patch serves as the anchor. It initializes the latent state and conditions each subsequent step, so older patches are folded into a representation that remains centered on recent evidence. A single shared module is reused at every step, so extending the scan further into the past introduces no additional parameters. Intermediate states retained during the scan allow the forecast head to weigh short and long portions of the history separately. This expresses recency through the order of recurrent refinement. Extensive experiments across multiple real-world time series datasets show that MARO achieves state-of-the-art performance on both long-term and short-term forecasting tasks.Ablation studies examine the contribution of the main architectural components.