Metraipolis › archive › dc_a46fce7c4348
TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH — arXiv:2608.16410
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16410
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:41:37.509Z
- SHA-256 of the archived text
fda1f9580e195924c9f3368f23a6ba9fa0ce65d66381e6148a33e5d76fabae66- Stable URL of this page
https://metraipolis.com/documento/dc_a46fce7c4348
How to cite
TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH — arXiv:2608.16410 — arXiv (en), https://arxiv.org/abs/2608.16410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a46fce7c4348 (Metraipolis archive dc_a46fce7c4348, sha256 fda1f9580e195924c9f3368f23a6ba9fa0ce65d66381e6148a33e5d76fabae66)
BibTeX
@misc{dca46fce7c4348,
title = {TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH — arXiv:2608.16410},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16410},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a46fce7c4348; sha256 fda1f9580e195924c9f3368f23a6ba9fa0ce65d66381e6148a33e5d76fabae66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active. In time-series forecasting, temporal choices, chronological validation, and costly evaluations further complicate this search. Controlled comparisons of heterogeneous search methods under a shared time-series CASH (TS-CASH) evaluation protocol remain limited. Within this setting, we study TRACECASH, a task-local hybrid sequential optimizer combining grouped actor-critic candidate generation with fixed rules for model coverage, validation-guided exploitation, and exploration after stalled progress. A model actor proposes an initial forecasting model; three model-conditioned actors generate temporal, architectural, and training actions; and a modelspecific decoder constructs the configuration ultimately evaluated. We compare TRACE-CASH with six alternatives spanning random, Bayesian, evolutionary, multi-objective, and language-model-assisted search across 41 dataset-frequency task variants. TRACE-CASH has the lowest mean rank on both MASE and WQL. Descriptively, it also has the lowest window-averaged test-MASE rank in the predefined full and late windows. These results support the complete TRACECASH procedure as competitive among the evaluated methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.16410 — 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 2026-10-18T19:02:44.172Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).