Metraipolis › archive › dc_cbb8b272e656
Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters — arXiv:2610.07834
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07834
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:41:26.293Z
- SHA-256 of the archived text
5dc4781570637bde696d2718ad019b8ef85618d8526e224edad1f320c943c012- Stable URL of this page
https://metraipolis.com/documento/dc_cbb8b272e656
How to cite
Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters — arXiv:2610.07834 — arXiv (en), https://arxiv.org/abs/2610.07834 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbb8b272e656 (Metraipolis archive dc_cbb8b272e656, sha256 5dc4781570637bde696d2718ad019b8ef85618d8526e224edad1f320c943c012)
BibTeX
@misc{dccbb8b272e656,
title = {Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters — arXiv:2610.07834},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07834},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbb8b272e656; sha256 5dc4781570637bde696d2718ad019b8ef85618d8526e224edad1f320c943c012},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07834. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster. Most existing methods build the retrieval memory once from the training segment, leaving observations revealed after deployment unavailable as references, and generally do not calibrate how much the retrieved information should influence a frozen forecaster. We identify two key determinants of retrieval utility for a frozen forecaster: whether the history still reflects the current state, and whether the correction it induces aligns with the forecaster's residual errors, an alignment that can shift between validation and deployment when the memory becomes stale. We propose FreshCast, a plug-in retrieval framework that keeps the forecaster frozen, continuously updates a non-parametric memory with new observations, forms a memory forecast through relational kernel regression, and calibrates its weight in closed form on the validation segment. Under a simplified generative model, we characterize the optimal combination gain through the second-order relation between forecaster error and memory correction, and show that a sufficiently long look-back can make periodic memory information redundant. Across seven benchmarks and ten forecasting architectures, FreshCast reduces average MSE for every evaluated forecaster and input length, by 14.6% and 5.6% at input lengths 96 and 720, and achieves lower MSE than the evaluated retrieval-augmented and online baselines in their comparison settings. Ablations show that freezing the memory at the end of training removes most of the gain, identifying post-training observations as a primary source of improvement. For a frozen forecaster, useful historical references must remain timely and provide information that helps correct its remaining errors. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07834 — 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 2026-10-07T11:19:24.792Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).