Metraipolis › archive › dc_822ac0296ff3

Towards Robust Time Series Learning via Capacity-Centric Modulation — arXiv:2609.39489

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39489
License (as archived)
CC0-1.0
Archived
2026-10-07T13:46:18.250Z
SHA-256 of the archived text
dec625d863777f0ca48fab191818444c0fd564a2479e1c93414458ce5d6e2b3e
Stable URL of this page
https://metraipolis.com/documento/dc_822ac0296ff3

How to cite

Towards Robust Time Series Learning via Capacity-Centric Modulation — arXiv:2609.39489 — arXiv (en), https://arxiv.org/abs/2609.39489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_822ac0296ff3 (Metraipolis archive dc_822ac0296ff3, sha256 dec625d863777f0ca48fab191818444c0fd564a2479e1c93414458ce5d6e2b3e)
BibTeX
@misc{dc822ac0296ff3,
  title = {Towards Robust Time Series Learning via Capacity-Centric Modulation — arXiv:2609.39489},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39489},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_822ac0296ff3; sha256 dec625d863777f0ca48fab191818444c0fd564a2479e1c93414458ce5d6e2b3e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to all samples, which can under-regularize corrupted samples and over-restrict clean samples. Common robustness approaches filter observations in data space or impose priors on latent representations. We propose Capacity-Centric Modulation (CCM) as a complementary, sample-adaptive regularization principle. Under this principle, we introduce SACM (Sample-Adaptive Capacity Modulation), a task-agnostic framework that exploits spectral sparsity to assign sample-wise dropout probabilities along internal activation paths. SACM integrates into existing backbones without architectural redesign and preserves the deterministic inference pipeline. Across 301 real-world dataset-backbone pairs covering 9 forecasting, 32 classification, and 4 anomaly-detection datasets, SACM reduces forecasting MSE by 6.7% on average and improves classification accuracy and point-adjusted F1 by 3.04% and 17.05%, respectively, relative to unmodified backbones, with zero test-time overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.39489 — 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 2026-10-07T13:18:10.398Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).