A balanced sampling strategy over statistically characterized time series patterns lets universal forecasting models train on 78 billion tokens instead of 419 billion, with equal or better zero-shot accuracy.
Title resolution pending
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
-
BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
A balanced sampling strategy over statistically characterized time series patterns lets universal forecasting models train on 78 billion tokens instead of 419 billion, with equal or better zero-shot accuracy.