{"ID":2893143,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13998","arxiv_id":"2507.13998","title":"ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies","abstract":"Modern multivariate time series forecasting primarily relies on two architectures: the Transformer with attention mechanism and Mamba. In natural language processing, an approach has been used that combines local window attention for capturing short-term dependencies and Mamba for capturing long-term dependencies, with their outputs averaged to assign equal weight to both. We find that for time-series forecasting tasks, assigning equal weight to long-term and short-term dependencies is not optimal. To mitigate this, we propose a dynamic weighting mechanism, ParallelTime Weighter, which calculates interdependent weights for long-term and short-term dependencies for each token based on the input and the model's knowledge. Furthermore, we introduce the ParallelTime architecture, which incorporates the ParallelTime Weighter mechanism to deliver state-of-the-art performance across diverse benchmarks. Our architecture demonstrates robustness, achieves lower FLOPs, requires fewer parameters, scales effectively to longer prediction horizons, and significantly outperforms existing methods. These advances highlight a promising path for future developments of parallel Attention-Mamba in time series forecasting. The implementation is readily available at: \\href{https://github.com/itay1551/ParallelTime}{GitHub}.","short_abstract":"Modern multivariate time series forecasting primarily relies on two architectures: the Transformer with attention mechanism and Mamba. In natural language processing, an approach has been used that combines local window attention for capturing short-term dependencies and Mamba for capturing long-term dependencies, with...","url_abs":"https://arxiv.org/abs/2507.13998","url_pdf":"https://arxiv.org/pdf/2507.13998v2","authors":"[\"Itay Katav\",\"Aryeh Kontorovich\"]","published":"2025-07-18T15:08:02Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":612035,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2893143,"paper_url":"https://arxiv.org/abs/2507.13998","paper_title":"ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies","repo_url":"https://github.com/itay1551/ParallelTime","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}