A single forecasting model can be trained to adapt its predictions to any target value interval at inference time by discretizing the output range during training and patching predictions at test time.
Using a financial training crite- rion rather than a prediction criterion.International journal of neural systems, 8(04):433–443, 1997
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
-
Goal-Oriented Time-Series Forecasting: Foundation Framework Design
A single forecasting model can be trained to adapt its predictions to any target value interval at inference time by discretizing the output range during training and patching predictions at test time.