BEAT adaptively scales gradients of frequency-specific networks during training to balance learning speeds, with reported gains on some long-term forecasting benchmarks.
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
REJECT 1representative citing papers
citing papers explorer
-
BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting
BEAT adaptively scales gradients of frequency-specific networks during training to balance learning speeds, with reported gains on some long-term forecasting benchmarks.