Metraipolis › archive › dc_db5fbb8cdbed

MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off — arXiv:2609.32656

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32656
License (as archived): CC0-1.0
Archived: 2026-10-07T20:55:51.230Z
SHA-256 of the archived text: 794a1af0f5c1473f373580465dbc952598f1d164863774d35397816c63b276b9
Stable URL of this page: https://metraipolis.com/documento/dc_db5fbb8cdbed

How to cite

MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off — arXiv:2609.32656 — arXiv (en), https://arxiv.org/abs/2609.32656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db5fbb8cdbed (Metraipolis archive dc_db5fbb8cdbed, sha256 794a1af0f5c1473f373580465dbc952598f1d164863774d35397816c63b276b9)

BibTeX

@misc{dcdb5fbb8cdbed,
  title = {MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off — arXiv:2609.32656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db5fbb8cdbed; sha256 794a1af0f5c1473f373580465dbc952598f1d164863774d35397816c63b276b9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another. Yet they are evaluated on a small fixed set of standard datasets whose cross-channel structure is rarely examined. We ask two questions: "How can we reliably measure lagged, non-linear, and joint coupling in MTSF datasets?" and "Do the standard datasets actually have such coupling?" To answer the first, we test four candidate measures on synthetic datasets with planted ground-truth coupling: Granger Causality (GC), Transfer Entropy (TE), lagged Mutual Information (MI), and the CD gain, a model-based measure we introduce that compares a channel-dependent (CD) model to its channel-independent (CI) variant. Only lagged MI and the CD gain recover every planted coupling. For the second question, the answer is a definite no, as the standard datasets have a median of only 23% lagged-coupled channel pairs and a median CD gain of -4.9%, compared to 78% and +4.6% on chaotic ODE systems. We therefore propose MixBench-TS, a benchmark of 10 real-world datasets with a median of 55.5% lagged-coupled pairs and a median CD gain of +1.7%. Across six state-of-the-art models tuned under one protocol, CI models win on 10/10 (MSE) and 8/10 (MAE) standard datasets, but on only 3/10 and 2/10 MixBench-TS datasets. We recommend using our benchmark for evaluating new CD models. Moreover, we propose profiling new datasets with lagged MI and the CD gain before using them to evaluate multivariate models. Code and data are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32656 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:00.904Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).