SiGMA unifies prior multi-scale methods into one operator family and proposes a learnable discrete Gaussian kernel that outperforms baselines on long- and short-term forecasting while using less time and memory.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalizing Multi-Scale Time-Series Modeling with a Single Operator
SiGMA unifies prior multi-scale methods into one operator family and proposes a learnable discrete Gaussian kernel that outperforms baselines on long- and short-term forecasting while using less time and memory.