A survey and M5 benchmark arguing that optimizing forecasts after generation, through ensembles and meta-learners, adds more value than replacing base forecasting models.
Xu Z, Zeng A, Xu Q (2023) FITS: Modeling Time Series with $10k$ Parameters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Forecast-Then-Optimize Deep Learning Methods
A survey and M5 benchmark arguing that optimizing forecasts after generation, through ensembles and meta-learners, adds more value than replacing base forecasting models.